Skip to content

Graph-Native Infrastructure for Context and Accountable AI Systems

security: SHA-pin all Actions, harden release pipeline, add pin verification (#824)

Mohd Kaifb59211ea7f8b
diff --git a/.github/dependabot.yml b/.github/dependabot.yml
index d1da3ddf..42a46136 100644
--- a/.github/dependabot.yml
+++ b/.github/dependabot.yml
@@ -70,6 +70,13 @@ updates:
- "dependencies"
- "github-actions"
- "ci"
+ # All our actions are SHA-pinned with a "# vX" comment; Dependabot
+ # resolves the new tag's SHA and updates both the pin and the comment
+ # together, so this stays the source of truth (no separate script needed).
+ groups:
+ github-actions:
+ patterns:
+ - "*"
# Optional dependencies (separate schedule for stability)
- package-ecosystem: "pip"
diff --git a/.github/scripts/verify-action-pins.sh b/.github/scripts/verify-action-pins.sh
new file mode 100644
index 00000000..5022297e
--- /dev/null
+++ b/.github/scripts/verify-action-pins.sh
@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+# Verifies that every third-party GitHub Action referenced in
+# .github/workflows/*.yml and .github/workflows/*.yaml is pinned to a full
+# commit SHA (not a mutable tag
+# or branch), and that any pin's trailing "# vX" comment still matches what
+# that tag resolves to today.
+#
+# Fails closed on purpose:
+# - a `uses:` line pinned to anything other than a 40-hex-char SHA is a
+# hard failure, not a skip - this is what stops a newly-added mutable
+# tag (e.g. `uses: some/action@v1`) from slipping past unnoticed.
+# - a tag that can't be resolved via the GitHub API (rate limit, deleted
+# tag, typo) is also a hard failure rather than a warning - an
+# unverifiable pin is exactly the failure mode this check exists to
+# catch, so it must not pass silently.
+set -uo pipefail
+
+fail=0
+checked=0
+
+# Pattern for a third-party uses: line — stored in a variable so bash's
+# [[ =~ ]] parser never sees literal \" or \' escapes, which cause a
+# "syntax error in conditional expression: unexpected token )" at runtime.
+# Semantics: optional leading quote, owner/repo, optional subpath, @ref,
+# optional trailing quote; quote chars excluded from the ref capture group.
+USES_PATTERN='uses:[[:space:]]+["'"'"']?([A-Za-z0-9_.-]+/[A-Za-z0-9_.-]+)(/[^[:space:]@"'"'"']+)?@([^[:space:]"'"'"']+)["'"'"']?'
+
+while IFS=: read -r file lineno content; do
+ # Local composite actions (./x) and Docker image refs (docker://...) use a
+ # different pinning mechanism and aren't in scope here.
+ [[ "$content" =~ uses:\ +\./ ]] && continue
+ [[ "$content" =~ uses:\ +docker:// ]] && continue
+
+ if [[ "$content" =~ $USES_PATTERN ]]; then
+ repo="${BASH_REMATCH[1]}"
+ ref="${BASH_REMATCH[3]}"
+ checked=$((checked + 1))
+
+ if [[ ! "$ref" =~ ^[0-9a-fA-F]{40}$ ]]; then
+ echo "::error file=$file,line=$lineno::$repo is pinned to '$ref', not a full commit SHA. Mutable tags/branches can be silently re-pointed (see the LiteLLM/Trivy 2026 incident) - pin to a commit SHA instead."
+ fail=1
+ continue
+ fi
+ sha="$ref"
+
+ if [[ "$content" =~ \#[[:space:]]*([^[:space:]]+)[[:space:]]*$ ]]; then
+ tag="${BASH_REMATCH[1]}"
+ else
+ echo "::warning file=$file,line=$lineno::$repo@$sha has no trailing '# vX' comment recording which tag it corresponds to - add one for auditability."
+ continue
+ fi
+
+ resolved=$(gh api "repos/$repo/commits/$tag" --jq '.sha' 2>/dev/null)
+ if [[ -z "$resolved" ]]; then
+ echo "::error file=$file,line=$lineno::Could not resolve '$repo@$tag' via the GitHub API (rate limit, deleted tag, or typo). Treating as unverifiable = failure."
+ fail=1
+ continue
+ fi
+
+ if [[ "$resolved" != "$sha" ]]; then
+ echo "::error file=$file,line=$lineno::$repo is pinned to $sha but tag '$tag' now resolves to $resolved. Update the pin or the comment."
+ fail=1
+ else
+ echo "OK $repo@$tag -> $sha ($file:$lineno)"
+ fi
+ fi
+done < <(grep -rHn "uses:" .github/workflows/*.yml .github/workflows/*.yaml 2>/dev/null)
+
+echo "Checked $checked action reference(s)."
+exit $fail
diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 3c79c367..f75c199a 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -13,12 +13,12 @@ jobs:
steps:
- name: Checkout Code
- uses: actions/checkout@v7
+ uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
fetch-depth: 0
- name: Set up Python 3.12
- uses: actions/setup-python@v7
+ uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
with:
python-version: "3.12"
cache: 'pip'
@@ -43,7 +43,7 @@ jobs:
# pytest-benchmark --storage file://benchmarks/results --benchmark-compare
- name: Upload Benchmark Results
- uses: actions/upload-artifact@v7
+ uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
if: always()
with:
name: benchmark-report-${{ github.run_id }}
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 4f51f1b7..18a246fb 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -21,11 +21,11 @@ jobs:
build:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v7
- - uses: actions/setup-python@v7
+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+ - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
with:
python-version: '3.11'
- - uses: actions/setup-node@v7
+ - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: '20'
cache: 'npm'
diff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.yml
index a78fbf42..c32d6955 100644
--- a/.github/workflows/codeql.yml
+++ b/.github/workflows/codeql.yml
@@ -20,7 +20,7 @@ jobs:
steps:
- name: Checkout repository
- uses: actions/checkout@v7
+ uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
# The CodeQL bundle download (github/codeql-action/init's "Setup CodeQL
# tools" step) streams a ~1GB tarball from GitHub's release CDN and
@@ -32,7 +32,7 @@ jobs:
# meaningful state carried over from a failed attempt.
- name: Initialize CodeQL (attempt 1)
id: codeql-init-1
- uses: github/codeql-action/init@v4
+ uses: github/codeql-action/init@d1ba80a13dd99fba24a470575428917156a28b43 # v4
continue-on-error: true
with:
languages: python
@@ -42,7 +42,7 @@ jobs:
- name: Initialize CodeQL (attempt 2)
id: codeql-init-2
if: steps.codeql-init-1.outcome == 'failure'
- uses: github/codeql-action/init@v4
+ uses: github/codeql-action/init@d1ba80a13dd99fba24a470575428917156a28b43 # v4
continue-on-error: true
with:
languages: python
@@ -52,17 +52,17 @@ jobs:
- name: Initialize CodeQL (attempt 3)
id: codeql-init-3
if: steps.codeql-init-2.outcome == 'failure'
- uses: github/codeql-action/init@v4
+ uses: github/codeql-action/init@d1ba80a13dd99fba24a470575428917156a28b43 # v4
with:
languages: python
queries: security-and-quality
config-file: .github/codeql/codeql-config.yml
- name: Autobuild
- uses: github/codeql-action/autobuild@v4
+ uses: github/codeql-action/autobuild@d1ba80a13dd99fba24a470575428917156a28b43 # v4
- name: Perform CodeQL Analysis
- uses: github/codeql-action/analyze@v4
+ uses: github/codeql-action/analyze@d1ba80a13dd99fba24a470575428917156a28b43 # v4
with:
category: "/language:python"
upload: false
@@ -72,7 +72,7 @@ jobs:
# Uploads results only when Default Setup is not active.
# If Default Setup is still enabled, this step skips gracefully
# instead of failing the workflow with HTTP 409.
- uses: github/codeql-action/upload-sarif@v4
+ uses: github/codeql-action/upload-sarif@d1ba80a13dd99fba24a470575428917156a28b43 # v4
with:
sarif_file: ${{ steps.codeql.outputs.sarif-output }}
category: "/language:python"
diff --git a/.github/workflows/defender-for-devops.yml b/.github/workflows/defender-for-devops.yml
index 0fd59ada..aa71bd69 100644
--- a/.github/workflows/defender-for-devops.yml
+++ b/.github/workflows/defender-for-devops.yml
@@ -36,14 +36,14 @@ jobs:
runs-on: windows-latest
steps:
- - uses: actions/checkout@v7
- - uses: actions/setup-dotnet@v6
+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+ - uses: actions/setup-dotnet@a98b56852c35b8e3190ac28c8c2271da59106c68 # v6
with:
dotnet-version: |
5.0.x
6.0.x
- name: Run Microsoft Security DevOps
- uses: microsoft/[email protected]
+ uses: microsoft/security-devops-action@08976cb623803b1b36d7112d4ff9f59eae704de0 # v1.12.0
id: msdo
with:
# checkov is intentionally excluded from this MSDO step.
@@ -57,11 +57,11 @@ jobs:
# avoiding the guardian.cmd/checkov exit-code bug in the MSDO wrapper.
tools: eslint,templateanalyzer,terrascan
- name: Upload results to Security tab
- uses: github/codeql-action/upload-sarif@v4
+ uses: github/codeql-action/upload-sarif@d1ba80a13dd99fba24a470575428917156a28b43 # v4
with:
sarif_file: ${{ steps.msdo.outputs.sarifFile }}
- - uses: actions/setup-python@v7
+ - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
with:
python-version: "3.12"
@@ -82,7 +82,7 @@ jobs:
}
- name: Upload Checkov results to Security tab
- uses: github/codeql-action/upload-sarif@v4
+ uses: github/codeql-action/upload-sarif@d1ba80a13dd99fba24a470575428917156a28b43 # v4
if: always()
with:
sarif_file: reports/checkov.sarif
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
index cc417a98..ca149d7e 100644
--- a/.github/workflows/docs.yml
+++ b/.github/workflows/docs.yml
@@ -29,11 +29,11 @@ jobs:
name: Validate Documentation
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v7
- - uses: actions/setup-python@v7
+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+ - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
with:
python-version: '3.11'
- - uses: actions/setup-node@v7
+ - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: '20'
- run: python docs_check.py
@@ -44,9 +44,9 @@ jobs:
runs-on: ubuntu-latest
needs: validate
steps:
- - uses: actions/checkout@v7
+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
- - uses: actions/setup-node@v7
+ - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: '20'
@@ -57,12 +57,12 @@ jobs:
cd ..
unzip -q export.zip -d site
- - uses: actions/configure-pages@v6
+ - uses: actions/configure-pages@45bfe0192ca1faeb007ade9deae92b16b8254a0d # v6
- - uses: actions/upload-pages-artifact@v5
+ - uses: actions/upload-pages-artifact@fc324d3547104276b827a68afc52ff2a11cc49c9 # v5
with:
path: ./site
- name: Deploy to GitHub Pages
id: deployment
- uses: actions/deploy-pages@v5
+ uses: actions/deploy-pages@cd2ce8fcbc39b97be8ca5fce6e763baed58fa128 # v5
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 6aaea2eb..df704ea3 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -5,19 +5,28 @@ on:
tags: ['v*']
permissions:
- contents: write
- id-token: write
+ contents: read
jobs:
release:
runs-on: ubuntu-latest
environment: pypi
+ concurrency:
+ group: release-${{ github.ref }}
+ cancel-in-progress: false
+ permissions:
+ contents: write # for the GitHub Release
+ id-token: write # for PyPI Trusted Publishing (OIDC) and attestation signing
+ attestations: write # for SLSA build provenance
+ # If you add another job to this workflow, give it its own explicit
+ # `permissions:` block rather than relying on the workflow-level default
+ # above (contents: read) - do not widen the workflow-level default.
steps:
- - uses: actions/checkout@v7
- - uses: actions/setup-python@v7
+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+ - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
with:
python-version: '3.11'
- - uses: actions/setup-node@v7
+ - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: '20'
cache: 'npm'
@@ -46,7 +55,11 @@ jobs:
print("Explorer frontend is packaged")
PY
- - uses: softprops/action-gh-release@v3
+ - name: Attest build provenance
+ uses: actions/attest-build-provenance@0f67c3f4856b2e3261c31976d6725780e5e4c373 # v4
+ with:
+ subject-path: 'dist/*'
+ - uses: softprops/action-gh-release@3d0d9888cb7fd7b750713d6e236d1fcb99157228 # v3
with:
files: dist/*
- - uses: pypa/gh-action-pypi-publish@release/v1
+ - uses: pypa/gh-action-pypi-publish@dc37677b2e1c63e2034f94d8a5b11f265b73ba33 # release/v1
diff --git a/.github/workflows/security-scan.yml b/.github/workflows/security-scan.yml
index d2ddd94e..ab742e76 100644
--- a/.github/workflows/security-scan.yml
+++ b/.github/workflows/security-scan.yml
@@ -28,13 +28,17 @@ jobs:
contents: read
security-events: write
actions: read
-
+ # Needed for the "Comment PR with Security Results" step below. Safe on
+ # pull_request (not pull_request_target): GitHub always forces a
+ # read-only token for PRs from forks regardless of this permission.
+ pull-requests: write
+
steps:
- name: Checkout repository
- uses: actions/checkout@v7
-
+ uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+
- name: Set up Python
- uses: actions/setup-python@v7
+ uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
with:
python-version: '3.11'
@@ -42,21 +46,50 @@ jobs:
run: |
python -m pip install --upgrade pip
pip install safety bandit semgrep jq
-
+ # Install the project itself (core deps + the LiteLLM provider extra)
+ # so Safety scans Semantica's actual dependency tree, not just the
+ # scanner tools' own dependencies.
+ pip install -e ".[llm-litellm]"
+
- name: Run Safety Check (Package Vulnerabilities)
run: |
- safety check --json --output safety-report.json || true
+ # NOTE: Safety 3.x repurposed --output to select a console format
+ # (json/text/screen/...), not a file path. Writing JSON to a file
+ # now requires --save-json; the previous `--output safety-report.json`
+ # usage was silently invalid and never produced a report.
+ safety check --save-json safety-report.json || true
+
+ # Guard 1: fail loudly if Safety exited before writing a report at all
+ # (network error, API auth failure, tool crash). Without this check a
+ # missing or empty file causes jq to fall back to "0", making a broken
+ # scanner indistinguishable from a clean scan.
+ if [ ! -s safety-report.json ]; then
+ echo "::error::Safety scan produced no report (safety-report.json is missing or empty). Treating as failure — check for network errors, API auth failures, or Safety crashes in the logs above."
+ exit 1
+ fi
+
echo "Checking for package vulnerabilities..."
-
- # Count vulnerabilities safely
- VULNS=$(safety check --json --output /dev/stdout 2>/dev/null | jq '.vulnerabilities | length' 2>/dev/null || echo "0")
-
+
+ # No || echo "0" fallback: if jq fails (malformed JSON, missing key,
+ # vulnerabilities:null) VULNS will be empty or "null" so guard 2 below
+ # catches it rather than silently treating the broken report as zero.
+ VULNS=$(jq '.vulnerabilities | length' safety-report.json 2>/dev/null)
+
+ # Guard 2: ensure VULNS is a non-negative integer before the -gt
+ # comparison. "null" (missing/null key) or "" (jq parse failure) would
+ # cause bash's -gt to throw an arithmetic error and fall through to the
+ # success branch — the same silent-pass bug as a missing file.
+ if ! [[ "$VULNS" =~ ^[0-9]+$ ]]; then
+ echo "::error::Safety report exists but 'vulnerabilities' is missing or non-numeric (got: '${VULNS}'). The report may be malformed or Safety may have written an error-only JSON. Treating as failure."
+ exit 1
+ fi
+
if [ "$VULNS" -gt 0 ]; then
echo "❌ Security vulnerabilities found: $VULNS"
echo "CI will fail to prevent merging of vulnerable dependencies"
echo ""
echo "Vulnerability details:"
- safety check || true
+ jq -r '.vulnerabilities[] | "- \(.package_name)==\(.analyzed_version): \(.vulnerability_id) (\(.CVE // "no CVE assigned"))"' safety-report.json || true
exit 1
else
echo "✅ No security vulnerabilities found"
@@ -99,9 +132,10 @@ jobs:
fi
- name: Upload Security Reports
- uses: actions/upload-artifact@v7
+ uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
with:
name: security-reports
+ retention-days: 14
path: |
safety-report.json
bandit-report.json
@@ -109,77 +143,91 @@ jobs:
- name: Comment PR with Security Results
if: github.event_name == 'pull_request'
- uses: actions/github-script@v9
+ uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9
with:
script: |
const fs = require('fs');
-
- // Read safety report
- let safetyResults = '';
- try {
- const safetyData = JSON.parse(fs.readFileSync('safety-report.json', 'utf8'));
- if (safetyData.vulnerabilities && safetyData.vulnerabilities.length > 0) {
- safetyResults = `## Safety Vulnerabilities Found\\n`;
- safetyData.vulnerabilities.forEach(vuln => {
- safetyResults += `- **${vuln.package}**: ${vuln.advisory}\\n`;
- });
- } else {
- safetyResults = '## No Safety Vulnerabilities Found\\n';
+
+ // Renders one tool's findings as a section. `items` is already
+ // the list of pre-formatted "- `thing` in `where`" strings; this
+ // just handles the found/not-found/report-missing framing and
+ // collapses long lists into a <details> block so the comment
+ // doesn't turn into a wall of text.
+ function renderSection(title, reportPath, parse) {
+ let data;
+ try {
+ data = JSON.parse(fs.readFileSync(reportPath, 'utf8'));
+ } catch (e) {
+ return [
+ `### ${title}`,
+ `⚠️ No report found at \`${reportPath}\` — the scan may have failed before producing output. Check the job logs.`,
+ ].join('\n');
}
- } catch (e) {
- safetyResults = '## Safety scan completed\\n';
- }
-
- // Read bandit report
- let banditResults = '';
- try {
- const banditData = JSON.parse(fs.readFileSync('bandit-report.json', 'utf8'));
- if (banditData.results && banditData.results.length > 0) {
- const highIssues = banditData.results.filter(issue => issue.issue_severity === 'HIGH');
- if (highIssues.length > 0) {
- banditResults = `## High Severity Security Issues Found\\n`;
- highIssues.forEach(issue => {
- banditResults += `- **${issue.test_name}**: ${issue.filename}:${issue.line_number}\\n`;
- });
- } else {
- banditResults = '## No High Severity Security Issues Found\\n';
- }
- } else {
- banditResults = '## No Bandit Issues Found\\n';
+
+ const items = parse(data);
+ if (items.length === 0) {
+ return [`### ${title}`, `✅ No findings.`].join('\n');
}
- } catch (e) {
- banditResults = '## Bandit scan completed\\n';
- }
-
- // Read semgrep report
- let semgrepResults = '';
- try {
- const semgrepData = JSON.parse(fs.readFileSync('semgrep-report.json', 'utf8'));
- if (semgrepData.results && semgrepData.results.length > 0) {
- semgrepResults = `## Security Patterns Found\\n`;
- semgrepData.results.slice(0, 10).forEach(issue => {
- semgrepResults += `- **${issue.rule_id}**: ${issue.path}\\n`;
- });
- if (semgrepData.results.length > 10) {
- semgrepResults += `- ... and ${semgrepData.results.length - 10} more\\n`;
- }
+
+ const lines = [`### ${title}`, `Found **${items.length}**.`, ''];
+ const shown = items.slice(0, 15);
+ if (items.length > 15) {
+ lines.push('<details>', '<summary>Show all findings</summary>', '');
+ lines.push(...items);
+ lines.push('', '</details>');
} else {
- semgrepResults = '## No Security Patterns Found\\n';
+ lines.push(...shown);
}
- } catch (e) {
- semgrepResults = '## Semgrep scan completed\\n';
+ return lines.join('\n');
}
-
- // Create summary comment
- const comment = `# 🔒 Security Scan Results\\n\\n${safetyResults}\\n\\n${banditResults}\\n\\n${semgrepResults}\\n\\n---\\n\\n*This security scan runs automatically on source-code PRs and bi-weekly (skipped for doc/markdown-only changes).*\\n\\n📊 **Security Policy**: CI fails on vulnerabilities and HIGH severity issues.`;
-
- // Post comment with error handling
+
+ const safetySection = renderSection(
+ 'Safety — dependency vulnerabilities',
+ 'safety-report.json',
+ (data) => (data.vulnerabilities || []).map(
+ (v) => `- \`${v.package_name}==${v.analyzed_version}\`: ${v.vulnerability_id}` +
+ (v.CVE ? ` (${v.CVE})` : '') + ` — ${v.advisory || 'no advisory text'}`
+ )
+ );
+
+ const banditSection = renderSection(
+ 'Bandit — HIGH-severity code issues',
+ 'bandit-report.json',
+ (data) => (data.results || [])
+ .filter((issue) => issue.issue_severity === 'HIGH')
+ .map((issue) => `- \`${issue.test_name}\` in \`${issue.filename}:${issue.line_number}\``)
+ );
+
+ const semgrepSection = renderSection(
+ 'Semgrep — static analysis patterns',
+ 'semgrep-report.json',
+ (data) => (data.results || []).map(
+ (issue) => `- \`${issue.check_id}\` in \`${issue.path}:${issue.start?.line ?? '?'}\``
+ )
+ );
+
+ const comment = [
+ '# 🔒 Security Scan Results',
+ '',
+ safetySection,
+ '',
+ banditSection,
+ '',
+ semgrepSection,
+ '',
+ '---',
+ '',
+ '*This security scan runs automatically on source-code PRs and bi-weekly (skipped for doc/markdown-only changes).*',
+ '',
+ '📊 **Security Policy**: CI fails on Safety vulnerabilities and Bandit HIGH-severity findings. Semgrep findings above are informational and do not block merge.',
+ ].join('\n');
+
try {
await github.rest.issues.createComment({
issue_number: context.issue.number,
owner: context.repo.owner,
repo: context.repo.repo,
- body: comment
+ body: comment,
});
console.log('✅ Security comment posted successfully');
} catch (error) {
diff --git a/.github/workflows/security.yml b/.github/workflows/security.yml
index d45bae3d..9f093bc7 100644
--- a/.github/workflows/security.yml
+++ b/.github/workflows/security.yml
@@ -12,8 +12,8 @@ jobs:
audit:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v7
- - uses: actions/setup-python@v7
+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+ - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
with:
python-version: '3.11'
- run: pip install pip-audit
diff --git a/.github/workflows/verify-action-pins.yml b/.github/workflows/verify-action-pins.yml
new file mode 100644
index 00000000..6e7dada9
--- /dev/null
+++ b/.github/workflows/verify-action-pins.yml
@@ -0,0 +1,28 @@
+name: Verify Action Pins
+
+on:
+ pull_request:
+ paths:
+ - '.github/workflows/**'
+ - '.github/scripts/verify-action-pins.sh'
+ push:
+ branches: [main]
+ paths:
+ - '.github/workflows/**'
+ - '.github/scripts/verify-action-pins.sh'
+ schedule:
+ - cron: '0 3 * * 1' # weekly, in case an upstream tag is deliberately moved
+ workflow_dispatch:
+
+permissions:
+ contents: read
+
+jobs:
+ verify:
+ runs-on: ubuntu-latest
+ steps:
+ - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
+ - name: Verify pinned action SHAs match their tag comments
+ env:
+ GH_TOKEN: ${{ github.token }}
+ run: bash .github/scripts/verify-action-pins.sh
diff --git a/CHANGELOG.md b/CHANGELOG.md
index badd93d8..389779fc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -168,6 +168,29 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- `GET /api/analytics` sets `response.status_code = 207` (Multi-Status) when some, but not all, of the requested metrics fail, and raises `HTTPException(500)` when every requested metric fails — a plain 2xx (including 207) reads as success to callers that only check `response.ok`, so an all-failed request now surfaces as a hard error rather than a body full of `{"error": ...}`
- Added regression tests covering all three failure paths (`test_patterns_failure_returns_500`, `test_analytics_partial_failure_returns_207`, `test_analytics_total_failure_returns_500`, and two `TestOntologyCreateFailures` cases)
+### Security
+
+- **CI/CD supply-chain hardening against mutable-tag Action compromise (LiteLLM/Trivy-class attack)** (#824) by @KaifAhmad1
+ - Every third-party GitHub Action across all 8 workflows is now pinned to a full commit SHA instead of a mutable tag (`@v7` → `@3d3c42e... # v7`), closing the exact vector used against LiteLLM in March 2026 (a compromised Trivy Action tag stole a long-lived publishing token)
+ - Added `verify-action-pins.yml` + `.github/scripts/verify-action-pins.sh`: a CI check that fails closed on any `uses:` reference that isn't a full SHA (catching a newly introduced mutable tag, not just auditing existing pins) and re-verifies every pin against the GitHub API on each workflow change, on push to `main`, and weekly; an unresolvable API lookup is treated as a failure rather than a silent skip
+ - `release.yml`: scoped `permissions` to the job level (workflow default is now `contents: read`), added a `concurrency` group so simultaneous tag pushes can't race the publish job, and added SLSA build provenance attestation (`actions/attest-build-provenance`) for every released wheel
+ - Created a protected `pypi` GitHub Environment (required reviewer, restricted to `v*` tag deployments) and enabled branch protection on `main` (required PR review with stale-approval dismissal, required status checks, no force-push/deletion, required conversation resolution) — PyPI publishing already used Trusted Publishing (OIDC) with no long-lived token
+ - Grouped Dependabot's `github-actions` updates into a single PR
+
+- **`security-scan.yml`'s Safety dependency-vulnerability check was silently non-functional** (#824) by @KaifAhmad1
+ - `safety check --json --output safety-report.json` is invalid in Safety 3.x (`--output` now selects a console format, not a file path); the command errored on every run, swallowed by `|| true`, so no report was ever produced and the job always fell back to a generic "scan completed" message with the vulnerability count hardcoded to 0
+ - Switched to `--save-json`, the correct flag for writing a JSON report to disk; also fixed `vuln.package` → `vuln.package_name` and Semgrep's `issue.rule_id` → `issue.check_id` (both produced `undefined` in the PR comment)
+ - The job never installed Semantica's own dependencies before scanning, so Safety was auditing the scanner tools' own transitive deps, not the project's; added `pip install -e ".[llm-litellm]"` so the actual dependency tree — including the LiteLLM extra — is what gets scanned
+ - Rewrote the PR-comment builder: every line previously used `\\n` inside JS template literals, which renders as the literal text `\n` rather than a newline, producing an unreadable wall of text; now builds real line arrays and collapses long finding lists into a `<details>` block
+ - Added the `pull-requests: write` permission the comment-posting step was missing (silently failing via its own try/catch on every prior run)
+
+- **`pypdf2==3.0.1` removed (CVE-2023-36464)** (#824) by @KaifAhmad1
+ - Surfaced by the Safety fix above: PyPDF2 is a discontinued project (merged into `pypdf`) permanently frozen at the vulnerable 3.0.1 with no patched release possible. `grep -rn "import PyPDF2"` found zero real usages anywhere in the codebase — it was only referenced in docstrings describing a `PyPDF2.PdfReader()` fallback for PDF parsing that was never actually implemented (`pdfplumber` does the real work). Removed the dependency and corrected the stale docstrings in `parse/__init__.py`, `parse/methods.py`, `parse/pdf_parser.py`, and `ingest/email_ingestor.py`
+
+- **10 Bandit B324 false positives suppressed (non-cryptographic MD5 use)** (#824) by @KaifAhmad1
+ - Surfaced by the same Safety fix restoring a working CI gate: Bandit's HIGH-severity check was blocking on 10 pre-existing `hashlib.md5()` calls, all generating short deterministic cache keys, entity IDs, or IRI suffixes from non-secret input — none used for passwords, tokens, or verifying untrusted data
+ - Bandit's own message suggests `usedforsecurity=False`, but that keyword argument needs Python 3.9+ and `pyproject.toml` declares `requires-python = ">=3.8"`; used a targeted `# nosec B324` with a one-line justification instead, which suppresses only this check with no runtime behavior change on any supported Python version
+
## [0.6.0] - 2026-07-21
### Added
diff --git a/SECURITY.md b/SECURITY.md
index 6945cde3..6b395811 100644
--- a/SECURITY.md
+++ b/SECURITY.md
@@ -112,6 +112,101 @@ We regularly update dependencies to address security vulnerabilities. However, y
- Be cautious with external API calls
- Implement proper authentication and authorization
+## CI/CD Supply-Chain Security
+
+Semantica's build and release pipeline is explicitly hardened against
+CI/CD supply-chain attacks — the class of attack behind the March 2026
+LiteLLM/Trivy incident, where a compromised third-party Action with a
+**mutable tag** was used to steal a long-lived publishing token, after which
+malicious packages were pushed straight to PyPI without ever touching the
+source repository. Every control below maps directly to closing one step of
+that attack chain.
+
+### Immutable build inputs
+
+- **Risk**: a tag (`@v4`, `@release/v1`) is re-pointed by a compromised upstream maintainer or account, silently changing what every consumer's CI runs.
+ **Control**: every third-party GitHub Action in every workflow is pinned to a full 40-character commit SHA, with the human-readable tag kept only as a trailing comment (e.g. `actions/checkout@3d3c42e... # v7`).
+- **Risk**: a SHA pin drifts out of sync with its own comment over time, or is mistyped.
+ **Control**: `verify-action-pins.yml` fails closed on any `uses:` reference that isn't a full commit SHA (catching a newly added mutable tag, not just auditing existing pins), resolves every pinned tag via the GitHub API on each workflow change, on every push to `main`, and weekly, and fails if the SHA no longer matches the tag it claims to be — an API lookup that can't be resolved is treated as a failure, not a silent skip.
+- **Risk**: manually re-pinning ~15 actions across 8 workflow files on every upstream release is error-prone.
+ **Control**: Dependabot (`github-actions` ecosystem) opens a grouped PR that bumps the SHA *and* the tag comment together whenever an action releases — pins never require hand-editing.
+
+### Publishing pipeline (highest-privilege path)
+
+- **Risk**: a long-lived `PYPI_TOKEN` sitting in repo/org secrets is exfiltrated by any compromised step.
+ **Control**: PyPI publishing uses Trusted Publishing (OIDC) (`id-token: write`) — there is no long-lived PyPI credential anywhere in this repository to steal.
+- **Risk**: a compromised CI run publishes to PyPI with no human in the loop.
+ **Control**: the publish job runs only inside a protected `pypi` GitHub Environment with a required human reviewer — every release needs manual approval in the Actions UI before it runs.
+- **Risk**: the release job could be triggered from an arbitrary branch/ref.
+ **Control**: the `pypi` environment's deployment-branch policy is restricted to `v*` tags only.
+- **Risk**: a scanner or unrelated job inherits publish-level credentials.
+ **Control**: `release.yml` sets `permissions: contents: read` at the workflow level; `contents: write` / `id-token: write` / `attestations: write` are granted only to the release job, never workflow-wide.
+- **Risk**: two tag pushes race through the publish pipeline simultaneously.
+ **Control**: `concurrency: group: release-${{ github.ref }}` serializes releases per tag.
+- **Risk**: a consumer can't verify a wheel on PyPI actually came from this repo's CI.
+ **Control**: SLSA build provenance is attested for every release via `actions/attest-build-provenance`, producing a signed, verifiable record of the exact commit and workflow run that produced the artifact (checkable with `gh attestation verify`).
+
+### Repository controls
+
+- **Risk**: unreviewed or force-pushed changes land on `main`.
+ **Control**: `main` requires 1 approving PR review (stale approvals dismissed on new pushes), resolved conversations, and blocks force-pushes and branch deletion.
+- **Risk**: a PR merges without its security/CI checks passing.
+ **Control**: merges require the `build`, `Analyze Python` (CodeQL), and `security-scan` checks to pass, in strict mode (checks must be re-run against the latest `main`).
+- **Risk**: a compromised scanner job reaches secrets or write access.
+ **Control**: scanning jobs (`CodeQL`, `security-scan.yml`, `security.yml`, `defender-for-devops.yml`) run with read-only, least-privilege permissions (typically `contents: read` + `security-events: write` only) and never share a job, environment, or secret scope with the publish job.
+- **Risk**: secrets are committed accidentally.
+ **Control**: GitHub secret scanning and push protection are both enabled at the repository level, rejecting pushes that contain recognizable credential patterns before they land in history.
+
+## Automated Security Scanning
+
+Every scan below runs continuously in CI, not just at release time:
+
+- **CodeQL** (`security-and-quality` query pack) — Python source: injection, unsafe deserialization, and other code-level vulnerability classes. Runs in `codeql.yml` on every push/PR to `main` and weekly.
+- **Bandit** — Python-specific security anti-patterns (hardcoded secrets, unsafe `eval`/`pickle`, weak crypto, etc.); CI fails on any HIGH-severity finding. Runs in `security-scan.yml` on every push/PR to `main` and twice weekly.
+- **Semgrep** (`p/security` ruleset) — cross-language static-analysis security patterns. Runs in `security-scan.yml` on every push/PR to `main` and twice weekly.
+- **Safety** — known CVEs in Semantica's own installed dependencies, including optional LLM-provider extras such as LiteLLM; CI fails on any match. Runs in `security-scan.yml` on every push/PR to `main` and twice weekly.
+- **pip-audit** — independent, PyPA-maintained vulnerability database cross-check against installed dependencies (Safety and pip-audit use different advisory sources, so both run). Runs in `security.yml` weekly.
+- **Microsoft Defender for DevOps** (`eslint`, `templateanalyzer`, `terrascan`) — JavaScript/TypeScript lint-security rules and infrastructure-as-code misconfigurations. Runs in `defender-for-devops.yml` on every push/PR to `main` and weekly.
+- **Checkov** — Kubernetes, Helm, Dockerfile, GitHub Actions, and secrets-pattern IaC scanning; results upload to the same Security tab as CodeQL. Runs in `defender-for-devops.yml` on every push/PR to `main` and weekly.
+- **GitGuardian** — secret-detection check on every pull request, installed as a GitHub App integration (not a repo-local workflow). Runs on every PR.
+- **GitHub secret scanning + push protection** — blocks known credential patterns before they're pushed, and continuously scans existing history. Platform-level, continuous.
+- **Dependabot** — version/security PRs for Python, Docker, and GitHub Actions dependencies, grouped where relevant to reduce review noise. Configured in `.github/dependabot.yml`, runs weekly for security-relevant packages and monthly for docs dependencies.
+- **`verify-action-pins.yml`** — enforces that every Action reference is a full commit SHA (failing on a newly introduced mutable tag) and confirms each SHA still matches the tag it claims to be. Runs on every workflow change, every push to `main`, and weekly.
+
+All SARIF-producing scanners (CodeQL, Checkov, Microsoft Defender) publish
+findings to the repository's **Security → Code scanning alerts** tab, giving
+a single audit trail across tools rather than scattered per-tool reports.
+
+### Adopting this posture in a fork or downstream deployment
+
+Teams standing up their own instance of Semantica, or forking it for an
+internal/regulated deployment, can reuse this posture directly:
+
+1. Keep Dependabot's `github-actions` ecosystem entry — it is what keeps
+ SHA pins current without manual maintenance.
+2. Re-run `verify-action-pins.yml` after re-pointing the repository's Actions
+ at your own mirrors, if you do so.
+3. If you publish your own PyPI package from a fork, configure your own
+ Trusted Publishing trust relationship on PyPI (Trusted Publishing is
+ scoped to a specific `owner/repo` + workflow filename) and your own
+ protected environment with your own required reviewers — these are not
+ transferable from this repository.
+4. Branch protection, environment protection, and repository secret
+ scanning are repository *settings*, not workflow files — cloning or
+ forking the repo does **not** copy them. They must be re-applied via
+ the GitHub UI or API on the new repository.
+5. GitHub secret scanning and push protection are repository settings that
+ don't carry over to a fork either — re-enable both under the new
+ repository's Security settings, not just Dependabot.
+6. GitGuardian runs as a GitHub App installation scoped to this specific
+ repository, not a workflow file — a fork gets no secret-detection
+ coverage from it until the app is installed separately on the new repo.
+7. CodeQL's `upload-sarif` step in `codeql.yml` only runs meaningfully if
+ Default Setup is *not* already enabled for the repository (it's designed
+ to skip gracefully otherwise) — check whether Default Setup or Advanced
+ Setup is active on the new repository and adjust expectations for where
+ CodeQL findings show up accordingly.
+
## Dependency Security Policy
### Regular Updates
diff --git a/pyproject.toml b/pyproject.toml
index d729e9b2..92b89a78 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -66,7 +66,6 @@ dependencies = [
"grpcio>=1.81.1",
"beautifulsoup4>=4.15.0",
"lxml>=6.1.1",
- "pypdf2>=2.10.0",
"python-docx>=1.2.0",
"openpyxl>=3.1.5",
"pillow>=12.2.0",
diff --git a/semantica/context/agent_memory.py b/semantica/context/agent_memory.py
index 53e5816c..2df42647 100644
--- a/semantica/context/agent_memory.py
+++ b/semantica/context/agent_memory.py
@@ -727,7 +727,7 @@ class AgentMemory:
timestamp = str(time.time())
random_str = str(hash(str(self.memory_items)) % 10000)
- memory_hash = hashlib.md5(f"{timestamp}_{random_str}".encode()).hexdigest()[:12]
+ memory_hash = hashlib.md5(f"{timestamp}_{random_str}".encode()).hexdigest()[:12] # nosec B324 - short unique ID, not security-sensitive
return f"mem_{memory_hash}"
diff --git a/semantica/context/context_graph.py b/semantica/context/context_graph.py
index ebfc0464..06419759 100644
--- a/semantica/context/context_graph.py
+++ b/semantica/context/context_graph.py
@@ -1691,7 +1691,7 @@ class ContextGraph:
# Fallback ID generation
import hashlib
- entity_hash = hashlib.md5(
+ entity_hash = hashlib.md5( # nosec B324 - deterministic entity ID, not security-sensitive
f"{entity_text}_{entity_type}".encode()
).hexdigest()[:12]
entity_id = f"{entity_type.lower()}_{entity_hash}"
diff --git a/semantica/context/entity_linker.py b/semantica/context/entity_linker.py
index 1cab04cc..eb35edd9 100644
--- a/semantica/context/entity_linker.py
+++ b/semantica/context/entity_linker.py
@@ -170,7 +170,7 @@ class EntityLinker:
uri = f"{self.base_uri}{uri_safe}"
else:
# Use hash of entity_id
- entity_hash = hashlib.md5(entity_id.encode()).hexdigest()[:8]
+ entity_hash = hashlib.md5(entity_id.encode()).hexdigest()[:8] # nosec B324 - deterministic URI suffix, not security-sensitive
uri = f"{self.base_uri}{entity_hash}"
# Add type if available
@@ -500,7 +500,7 @@ class EntityLinker:
def _generate_entity_id(self, text: str, entity_type: str) -> str:
"""Generate entity ID from text and type."""
- entity_hash = hashlib.md5(f"{text}_{entity_type}".encode()).hexdigest()[:12]
+ entity_hash = hashlib.md5(f"{text}_{entity_type}".encode()).hexdigest()[:12] # nosec B324 - deterministic entity ID, not security-sensitive
return f"{entity_type.lower()}_{entity_hash}"
def build_entity_web(self) -> Dict[str, Any]:
diff --git a/semantica/graph_store/graph_store.py b/semantica/graph_store/graph_store.py
index 2d185c19..5b7e2637 100644
--- a/semantica/graph_store/graph_store.py
+++ b/semantica/graph_store/graph_store.py
@@ -294,7 +294,7 @@ class QueryEngine:
import hashlib
key_str = f"{query}:{str(parameters)}"
- return hashlib.md5(key_str.encode()).hexdigest()
+ return hashlib.md5(key_str.encode()).hexdigest() # nosec B324 - cache key, not security-sensitive
def clear_cache(self) -> None:
"""Clear query cache."""
@@ -1056,7 +1056,7 @@ class GraphStore:
if not entity_id and entity_text:
import hashlib
- entity_hash = hashlib.md5(
+ entity_hash = hashlib.md5( # nosec B324 - deterministic entity ID, not security-sensitive
f"{entity_text}_{entity_type}".encode()
).hexdigest()[:12]
entity_id = f"{entity_type.lower()}_{entity_hash}"
diff --git a/semantica/ingest/email_ingestor.py b/semantica/ingest/email_ingestor.py
index 0b453def..81c2af20 100644
--- a/semantica/ingest/email_ingestor.py
+++ b/semantica/ingest/email_ingestor.py
@@ -180,7 +180,7 @@ class AttachmentProcessor:
This method attempts to extract text content from various document
types. Currently supports plain text files. PDF and Word document
- extraction would require additional libraries (PyPDF2/pdfplumber for
+ extraction would require additional libraries (pdfplumber for
PDF, python-docx for Word).
Args:
@@ -193,9 +193,9 @@ class AttachmentProcessor:
"""
try:
if file_type == "application/pdf":
- # PDF text extraction would require PyPDF2 or pdfplumber
+ # PDF text extraction would require pdfplumber
self.logger.debug(
- "PDF text extraction not implemented (requires PyPDF2/pdfplumber)"
+ "PDF text extraction not implemented (requires pdfplumber)"
)
return None
elif file_type in [
diff --git a/semantica/ontology/namespace_manager.py b/semantica/ontology/namespace_manager.py
index f7ed0047..69f26c66 100644
--- a/semantica/ontology/namespace_manager.py
+++ b/semantica/ontology/namespace_manager.py
@@ -120,7 +120,7 @@ class NamespaceManager:
# Use hash-based IRI
import hashlib
- hash_id = hashlib.md5(class_name.encode()).hexdigest()[:8]
+ hash_id = hashlib.md5(class_name.encode()).hexdigest()[:8] # nosec B324 - deterministic IRI suffix, not security-sensitive
iri = urljoin(self.get_base_uri(), f"class/{hash_id}")
return iri
@@ -146,7 +146,7 @@ class NamespaceManager:
# Use hash-based IRI
import hashlib
- hash_id = hashlib.md5(property_name.encode()).hexdigest()[:8]
+ hash_id = hashlib.md5(property_name.encode()).hexdigest()[:8] # nosec B324 - deterministic IRI suffix, not security-sensitive
iri = urljoin(self.get_base_uri(), f"property/{hash_id}")
return iri
@@ -170,7 +170,7 @@ class NamespaceManager:
else:
import hashlib
- hash_id = hashlib.md5(individual_name.encode()).hexdigest()[:8]
+ hash_id = hashlib.md5(individual_name.encode()).hexdigest()[:8] # nosec B324 - deterministic IRI suffix, not security-sensitive
iri = urljoin(self.get_base_uri(), f"individual/{hash_id}")
return iri
diff --git a/semantica/parse/__init__.py b/semantica/parse/__init__.py
index 5091f562..7890b3ae 100644
--- a/semantica/parse/__init__.py
+++ b/semantica/parse/__init__.py
@@ -8,7 +8,7 @@ emails, code files, and media files.
Algorithms Used:
Document Parsing:
- - PDF Parsing: pdfplumber integration (pdfplumber.PDF()) for text extraction, PyPDF2.PdfReader() fallback, table extraction (pdfplumber.extract_tables()), image extraction, metadata extraction (title, author, dates via pdf.metadata), page-level processing (page iteration)
+ - PDF Parsing: pdfplumber integration (pdfplumber.PDF()) for text extraction, table extraction (pdfplumber.extract_tables()), image extraction, metadata extraction (title, author, dates via pdf.metadata), page-level processing (page iteration)
- DOCX Parsing: python-docx integration (docx.Document()), paragraph extraction (document.paragraphs), table extraction (docx.table.Table), section/heading detection (paragraph.style), metadata extraction (core_properties), formatting extraction
- Docling Parsing: Docling integration (DocumentConverter.convert()) for enhanced table extraction and document structure understanding, supports PDF, DOCX, PPTX, XLSX, HTML, images, markdown/HTML/JSON export formats, OCR support (optional dependency)
- PPTX Parsing: python-pptx integration (pptx.Presentation()), slide extraction (presentation.slides), shape extraction, notes extraction, metadata extraction
@@ -45,7 +45,7 @@ Media Parsing:
- Audio/Video Parsing: Metadata extraction (format, duration, codec), file information extraction (future support)
Format-Specific Parsers:
- - PDFParser: pdfplumber.PDF() for text/tables, PyPDF2.PdfReader() fallback, page iteration (pdf.pages), metadata extraction
+ - PDFParser: pdfplumber.PDF() for text/tables, page iteration (pdf.pages), metadata extraction
- DOCXParser: docx.Document() for document loading, paragraph iteration, table extraction, core_properties access
- DoclingParser: DocumentConverter.convert() for multi-format parsing with enhanced table extraction, supports PDF/DOCX/PPTX/XLSX/HTML/images, markdown/HTML/JSON export (optional dependency)
- PPTXParser: pptx.Presentation() for presentation loading, slide iteration, shape extraction
diff --git a/semantica/parse/methods.py b/semantica/parse/methods.py
index 0fddd607..e83cf6ff 100644
--- a/semantica/parse/methods.py
+++ b/semantica/parse/methods.py
@@ -49,7 +49,7 @@ Media Parsing:
Algorithms Used:
Document Parsing:
- - PDF Parsing: pdfplumber integration (pdfplumber.PDF()) for text extraction, PyPDF2.PdfReader() fallback, table extraction (pdfplumber.extract_tables()), image extraction, metadata extraction (title, author, dates via pdf.metadata), page-level processing (page iteration)
+ - PDF Parsing: pdfplumber integration (pdfplumber.PDF()) for text extraction, table extraction (pdfplumber.extract_tables()), image extraction, metadata extraction (title, author, dates via pdf.metadata), page-level processing (page iteration)
- DOCX Parsing: python-docx integration (docx.Document()), paragraph extraction (document.paragraphs), table extraction (docx.table.Table), section/heading detection (paragraph.style), metadata extraction (core_properties), formatting extraction
- HTML Parsing: BeautifulSoup integration (BeautifulSoup(html, 'html.parser')), text extraction (soup.get_text()), link extraction (find_all('a')), metadata extraction (meta tags), structure analysis
- Text Parsing: Plain text file reading (open().read()), encoding detection, line-by-line processing
@@ -83,7 +83,7 @@ Media Parsing:
- Audio/Video Parsing: Metadata extraction (format, duration, codec), file information extraction (future support)
Format-Specific Parsers:
- - PDFParser: pdfplumber.PDF() for text/tables, PyPDF2.PdfReader() fallback, page iteration (pdf.pages), metadata extraction
+ - PDFParser: pdfplumber.PDF() for text/tables, page iteration (pdf.pages), metadata extraction
- DOCXParser: docx.Document() for document loading, paragraph iteration, table extraction, core_properties access
- JSONParser: json.load()/json.loads(), recursive structure traversal, path extraction
- CSVParser: csv.DictReader() for row-by-row processing, delimiter detection, header handling
diff --git a/semantica/parse/pdf_parser.py b/semantica/parse/pdf_parser.py
index 7ad31ced..639f60a9 100644
--- a/semantica/parse/pdf_parser.py
+++ b/semantica/parse/pdf_parser.py
@@ -1,7 +1,7 @@
"""
PDF Document Parser Module
-This module handles PDF document parsing using PyPDF2 and pdfplumber for text,
+This module handles PDF document parsing using pdfplumber for text,
table, and image extraction, including metadata and page-level processing.
Key Features:
diff --git a/semantica/triplet_store/query_engine.py b/semantica/triplet_store/query_engine.py
index f0e908c2..5ddfe087 100644
--- a/semantica/triplet_store/query_engine.py
+++ b/semantica/triplet_store/query_engine.py
@@ -527,7 +527,7 @@ class QueryEngine:
import hashlib
normalized = " ".join(query.split())
- return hashlib.md5(normalized.encode()).hexdigest()
+ return hashlib.md5(normalized.encode()).hexdigest() # nosec B324 - cache key, not security-sensitive
def _cache_result(self, query: str, result: QueryResult) -> None:
"""Cache query result."""