agentic-actions-auditor agent skill by trailofbits
Audits GitHub Actions workflows for security vulnerabilities where attacker-controlled input reaches AI agents like Claude Code Action, Gemini CLI, or Codex in CI/CD.
At a glance
| Publisher | Trail of Bits Official |
|---|---|
| Repository | trailofbits/skills (83 listed skills) |
| Category | Security |
| License | CC-BY-SA-4.0 |
| Last commit | October 15, 2026 (repository) |
| SKILL.md | 319 lines, 2,871 words |
| Bundled files | 15 files, including references, assets or templates |
| Quality score | 89/100 · B Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the badges for this listing |
Before you install
Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: none.
- Tool permissions requested:
Read Grep Glob Bash(theallowed-toolsfield of SKILL.md). - License: CC-BY-SA-4.0, an open-source or open-content license.
Install agentic-actions-auditor
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/trailofbits/skills/tree/main/plugins/agentic-actions-auditor/skills/agentic-actions-auditortmp="$(mktemp -d)"
git clone --depth 1 https://github.com/trailofbits/skills.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"plugins/agentic-actions-auditor/skills/agentic-actions-auditor .claude/skills/
rm -rf "$tmp"python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo trailofbits/skills \
--path plugins/agentic-actions-auditor/skills/agentic-actions-auditortrailofbits/skills is third-party code. Read SKILL.md and any bundled scripts before you install it.
How the author describes it
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
From the description field of SKILL.md. Agents read this line to decide when to load the skill.
Sections in SKILL.md
- When to Use
- When NOT to Use
- Rationalizations to Reject
- Audit Methodology
- Step 0: Determine Analysis Mode
- Step 1: Discover Workflow Files
- Step 2: Identify AI Action Steps
- Step 3: Capture Security Context
- Step 4: Analyze for Attack Vectors
- Step 5: Report Findings
- Detailed References
Files in the skill folder
SKILL.mdagents/openai.yamlassets/trail-of-bits-mark.svgreferences/action-profiles.mdreferences/cross-file-resolution.mdreferences/foundations.mdreferences/vector-a-env-var-intermediary.mdreferences/vector-b-direct-expression-injection.mdreferences/vector-c-cli-data-fetch.mdreferences/vector-d-pr-target-checkout.mdreferences/vector-e-error-log-injection.mdreferences/vector-f-subshell-expansion.mdreferences/vector-g-eval-of-ai-output.mdreferences/vector-h-dangerous-sandbox-configs.mdreferences/vector-i-wildcard-allowlists.md
Suede Skill Check: 89/100 · B
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: 5c99c03fb8a9. Report version ed3174078836. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
- Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
- Bundled scripts: 0 of 2 points. 2 when the skill folder ships a scripts/ folder.
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
agentic-actions-auditor passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 5 of 5 |
| Boundary clause | 0 of 4 |
| Example request | 0 of 3 |
| Instruction depth | 7 of 7 |
| Reference files | 3 of 3 |
| Bundled scripts | 0 of 2 |
| Recent maintenance | 9 of 9 |
| Curated-list citations | 7 of 7 |
| Tool permissions declared | 2 of 2 |
| Compatibility declared | 0 of 2 |
Two badges for agentic-actions-auditor
Choose the numeric badge, the letter badge, or both. Each links to this skill’s Suede listing; either valid linked badge can qualify for the feature offer.
[](https://skills.suedeai.ai/directory/trailofbits/skills/agentic-actions-auditor/)
[](https://skills.suedeai.ai/directory/trailofbits/skills/agentic-actions-auditor/)<a href="https://skills.suedeai.ai/directory/trailofbits/skills/agentic-actions-auditor/"><img src="https://skills.suedeai.ai/directory/trailofbits/skills/agentic-actions-auditor/score.svg" alt="Suede Skill Check: 89/100" width="160" height="175"></a>
<a href="https://skills.suedeai.ai/directory/trailofbits/skills/agentic-actions-auditor/"><img src="https://skills.suedeai.ai/directory/trailofbits/skills/agentic-actions-auditor/badge.svg" alt="Suede Skill Check: Grade B" width="160" height="175"></a>Suede Certified on the shield refers to this published structural quality check. Security scan: not scanned. Read the methodology.
Limited-time feature offer: display either the numeric or letter badge in your repository or skill README (both also qualify), then request badge verification. Eligible skills scoring 80–99 can receive a featured placement after Suede verifies at least one valid badge linked to the skill’s listing. Suede has not announced an end date.
Where this skill is cited
trailofbits/skills appears in 4 curated lists: BehiSecc/awesome-claude-skills, heilcheng/awesome-agent-skills, hesreallyhim/awesome-claude-code, travisvn/awesome-claude-skills.