106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.
Shell agent-skillsai-agentsclaudeclaude-codeclaude-skillscontent-creationgemini-cli-extensioninstagramlinkedinllmmarketingmarketing-skillsmcpopenclawsocial-mediasocial-media-marketingtiktok
Add OpenSSF Scorecard workflow and security policy
FH3WEe23d7e427673
diff --git a/.github/workflows/scorecard.yml b/.github/workflows/scorecard.ymlnew file mode 100644index 0000000..7af4c1b--- /dev/null+++ b/.github/workflows/scorecard.yml@@ -0,0 +1,32 @@+name: OpenSSF Scorecard++on:+ branch_protection_rule:+ schedule:+ - cron: "30 4 * * 1"+ push:+ branches: [main]+ workflow_dispatch:++permissions: read-all++jobs:+ analysis:+ runs-on: ubuntu-latest+ permissions:+ security-events: write # upload SARIF to code scanning+ id-token: write # required to publish results to scorecard.dev+ steps:+ - uses: actions/checkout@v4+ with:+ persist-credentials: false+ - name: Run Scorecard analysis+ uses: ossf/[email protected]+ with:+ results_file: results.sarif+ results_format: sarif+ publish_results: true+ - name: Upload to code scanning+ uses: github/codeql-action/upload-sarif@v3+ with:+ sarif_file: results.sarifdiff --git a/SECURITY.md b/SECURITY.mdnew file mode 100644index 0000000..36131c4--- /dev/null+++ b/SECURITY.md@@ -0,0 +1,19 @@+# Security Policy++This repository contains Markdown skill files and small build scripts — no runtime code,+no dependencies, no credentials. The main security consideration for users is that skills+instruct AI agents: review any skill before installing it, exactly as you would a script.++## Reporting++Found something concerning — a skill that could induce unsafe agent behavior, a prompt-injection+vector, or an issue in the build scripts? Please report it privately via+[GitHub Security Advisories](https://github.com/social-media-skills/skills/security/advisories/new)+rather than a public issue. We aim to respond within 72 hours.++## Scope++- Skills that could cause an agent to act without user confirmation, exfiltrate data, or+ follow instructions embedded in fetched content — highest priority.+- Build/validation script issues (`scripts/`).+- Out of scope: the behavior of third-party tools the skills describe (report those upstream).