Agent skill · GitHub (community contributions)

GitHub Actions Hardening skill for Claude Code, Codex and Cursor

Reviews workflow files for script injection, risky triggers and over-broad permissions.

Communityname: github-actions-hardening★ 40k (repo)pushed 2026-10-23MITSKILL.md on GitHubchecked 2026-11-07

What it does, in the publisher's words

Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens.

The description field of the SKILL.md. The agent reads only this at startup and decides from it when to load the full skill.

Install GitHub Actions Hardening

The skills CLI copies the skill into the folder of each agent you pick (Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf...). Add -g for all projects. Needs Node.js 22.20+. docs

npx skills add github/awesome-copilot --skill github-actions-hardening

Works with

Claude Code, Claude.ai and Claude Desktop, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and other agents that read the open Agent Skills format.

What's in the SKILL.md

13 sections
  • When to Use This Skill
  • The Core Insight
  • Execution Workflow
  • Step 1 — Map the Triggers and Trust Level
  • Step 2 — Hunt for Script Injection
  • Step 3 — Check Privileged Triggers Don't Execute Untrusted Code
  • Step 4 — Audit permissions:
  • Step 5 — Audit Action References (Supply Chain)
  • Step 6 — Check Secret and Output Handling
  • Step 7 — Produce the Report
  • Severity Guide
  • Output Rules
  • Reference Files

Bundled files

5
  • references/injection.md
  • references/permissions-and-tokens.md
  • references/report-format.md
  • references/supply-chain.md
  • references/triggers-and-privilege.md

Loaded only when the instructions point to them.

Facts

Skill name
github-actions-hardening
Publisher
GitHub (community contributions) (community)
Repo
github/awesome-copilot
License
MIT
SKILL.md size
1,241 words, 156 lines
Bundled files
5, 5 docs
Repo stars
40k (as of 2026-10-24)
SKILL.md checked
2026-11-07

Pairs with the GitHub Actions MCP server: the server gives the agent the tools, the skill teaches it how to use them.

More skills from github/awesome-copilot

  • Git Commit: Reads the diff, stages related files and writes conventional commits, splitting when needed.

Related security & auth skills

FAQ

What does the github-actions-hardening skill do?+

Reviews workflow files for script injection, risky triggers and over-broad permissions. In its own SKILL.md, GitHub (community contributions) describes it as: "Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped..."

How do I install the github-actions-hardening skill?+

Run npx skills add github/awesome-copilot --skill github-actions-hardening and pick your agents, or use the tab for your agent above. In Claude Code the skill ends up in ~/.claude/skills/github-actions-hardening/SKILL.md; in Codex and Cursor in .agents/skills/github-actions-hardening/.

Does GitHub Actions Hardening work in Codex, Cursor and Copilot, or only Claude?+

It's a standard SKILL.md, so any agent that reads the Agent Skills format can use it: Claude Code, the Claude apps, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and more.

Who maintains GitHub Actions Hardening?+

GitHub (community contributions) (a community project), in the github/awesome-copilot repo on GitHub, last pushed 2026-10-23. License: MIT.

Read a skill's SKILL.md and scripts before you install it: skills aren't verified by any agent vendor. Claude skills marketplace · How to install skills · MCP servers