OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
TypeScript ai-securityapplication-securityclicode-scanningcodexcodex-securitycybersecuritydevsecopsnodejsnpmopenaisdksecuritytypescriptvulnerability-scanning
docs(plugin): add a guide to security skills (#2586)
Michael D'Angelo5f5b5f225e04
diff --git a/evals/workflow-routing/harness.mts b/evals/workflow-routing/harness.mtsindex 0c69831fb..8b102b81b 100644--- a/evals/workflow-routing/harness.mts+++ b/evals/workflow-routing/harness.mts@@ -31,7 +31,14 @@ export async function prepareRoutingEval(root: string) {});}const skills: Skill[] = [];- for (const name of (await readdir(join(runtime, "skills"))).sort()) {+ const entries = await readdir(join(runtime, "skills"), {+ withFileTypes: true,+ });+ const skillNames = entries+ .filter((entry) => entry.isDirectory())+ .map((entry) => entry.name)+ .sort();+ for (const name of skillNames) {const source = await readFile(join(runtime, "skills", name, "SKILL.md"),"utf8",diff --git a/plugins/codex-security/skills/README.md b/plugins/codex-security/skills/README.mdnew file mode 100644index 000000000..dcb8a1560--- /dev/null+++ b/plugins/codex-security/skills/README.md@@ -0,0 +1,41 @@+# Codex Security skills++With the plugin enabled, you can ask Codex to "check my uncommitted changes for security bugs." To pick the skill yourself, include its name in the request, as in `$security-diff-scan`. [Setup and CLI examples](../../../docs/agent-workflows.md)++## Choosing a scan++- [security-scan](security-scan/SKILL.md) audits a repo or folder in one pass. Start here for a general review.+- [security-diff-scan](security-diff-scan/SKILL.md) looks for vulnerabilities introduced or exposed by a PR, commit, branch diff, or local edits.+- [deep-security-scan](deep-security-scan/SKILL.md) makes several passes over the same code and combines the findings in one report.++## Before you merge or install something++- [assess-patch-risk](assess-patch-risk/SKILL.md) takes a patch file, PR diff, or commit range. It explains what could break, whether the tests would catch it, and whether the patch is ready to merge.+- [check-skills](check-skills/SKILL.md) reviews a downloaded agent skill before you install it. Open Codex in a separate, trusted workspace and point it to the skill folder. It reads the instructions and scripts without running them.++## Security policy and threat models++- [define-security-policy](define-security-policy/SKILL.md) writes or updates `SECURITY.md` in the repo root or a component folder. Use it to set the rules for future reviews, including what counts as a finding and what's out of scope.+- [threat-model](threat-model/SKILL.md) maps what the current code protects and where an attacker could get in. Look for `threatmodel.md` in the scan output directory, or in the plugin's artifact storage for that repo if you run the skill on its own.+- [threat-model-visualize](threat-model-visualize/SKILL.md) turns an existing model into a diagram you can explore.++## Investigating a finding++- [triage-finding](triage-finding/SKILL.md) checks a reported bug against your code and security policy. Give it the alert or ticket.+- [resolve-dependency-alert](resolve-dependency-alert/SKILL.md) traces what pulled a flagged package into your checkout or image and checks your upgrade options.+- [finding-discovery](finding-discovery/SKILL.md) looks for possible vulnerabilities in a path or diff and flags what still needs proof.+- [validation](validation/SKILL.md) checks whether a suspected bug is real by tracing the code or trying to reproduce it.+- [attack-path-analysis](attack-path-analysis/SKILL.md) traces how an attacker could trigger the bug and what they'd gain.++## Fixing a bug++- [fix-finding](fix-finding/SKILL.md) patches a vulnerability and checks that the fix stops the attack and preserves normal use.+- [verify-fix](verify-fix/SKILL.md) checks an existing fix. Give it the original finding and the current checkout to see whether the fix worked or what evidence is missing.+- [propose-security-hardening](propose-security-hardening/SKILL.md) compares design changes that could keep the same kind of bug from turning up again.++## Reports and tickets++- [vulnerability-writeup](vulnerability-writeup/SKILL.md) turns notes or a proof of concept into a report explaining the bug, its impact, and the evidence.+- [publish-findings](publish-findings/SKILL.md) previews alerts from another scanner and imports them into the local workbench. Some formats also support import into Codex Security Cloud.+- [cloud-findings](cloud-findings/SKILL.md) looks up a finding, report, or scan status in your connected Cloud account. You can paste a finding link.+- [track-findings](track-findings/SKILL.md) takes validated findings from a completed scan directory and checks for existing tickets. You review any new Linear, Jira, or GitHub issues before it files them. It can also draft a GitHub security advisory.