Scan reports · trailofbits/skills
agentic-actions-auditor: scan report
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… An automated scan of this public skill from trailofbits/skills: security, token cost, spec and clarity, with every finding and its fix.
Result
Verdict
50/100 · grade F
trailofbits/skills/plugins/agentic-actions-auditor/skills/agentic-actions-auditor at 5c99c03
Spec 25 · Efficiency 0 · Clarity 25 · Security 0 (each out of 25)
Always loaded 149 tokens · on trigger 5,271 · on demand 18,729
sec/permissionswarn · SKILL.md:190Escalates permissions.sec/permissionswarn · references/action-profiles.md:56Escalates permissions.sec/remote-execwarn · references/vector-f-subshell-expansion.md:51Downloads and executes remote code. Reads as an example or a warning here; check it in context.eff/body-tokenswarn · SKILL.md~5271 tokens load every time this triggers. Aim for under 5,000; split into reference files read on demand.sec/exfiltrationwarn · references/vector-g-eval-of-ai-output.md:78Sends a secret in a request. Normal for API auth; check the host is the service the key belongs to.eff/orphan-fileinfo · references/action-profiles.mdreferences/action-profiles.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/cross-file-resolution.mdreferences/cross-file-resolution.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/foundations.mdreferences/foundations.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-a-env-var-intermediary.mdreferences/vector-a-env-var-intermediary.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-b-direct-expression-injection.mdreferences/vector-b-direct-expression-injection.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-c-cli-data-fetch.mdreferences/vector-c-cli-data-fetch.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-d-pr-target-checkout.mdreferences/vector-d-pr-target-checkout.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-e-error-log-injection.mdreferences/vector-e-error-log-injection.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-f-subshell-expansion.mdreferences/vector-f-subshell-expansion.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-g-eval-of-ai-output.mdreferences/vector-g-eval-of-ai-output.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-h-dangerous-sandbox-configs.mdreferences/vector-h-dangerous-sandbox-configs.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · references/vector-i-wildcard-allowlists.mdreferences/vector-i-wildcard-allowlists.md is never mentioned in SKILL.md, so the agent won't know to read it.
Where it comes from
Source
| Fact | Value |
|---|---|
| Repository | trailofbits/skills |
| Skill folder | plugins/agentic-actions-auditor/skills/agentic-actions-auditor |
| Stars | 7,641 |
| License | CC-BY-SA-4.0 |
| Commit scanned | 5c99c03 |
| Scanned | 2026-10-19 |
| Files | 14 |
ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.
For maintainers
Badge for the README
If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.
[](https://proskills.dev/reports/trailofbits-agentic-actions-auditor)
Alternatives
Scanned alternatives on ProSkills
Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.
- AGENTS.md ArchitectA short instructions file from your real repo.Loads when the user writes, rewrites or audits CLAUDE.md, AGENTS.md or rules files.5 rules · Agent OpsScan 100Free
- CI Pipeline BuilderFast, locked-down CI. GitHub Actions first.Loads when the user builds, speeds up or hardens a CI pipeline.5 rules · DevOps & CloudScan 100$12
- Security ReviewExploit sketch, severity and fix for each finding.Loads when the change touches auth, user input, outbound requests, secrets or an LLM feature.5 rules · Code ReviewScan 100$12
Same repository
More from trailofbits/skills
- algorand-vulnerability-scannerGrade A100/100
- audit-context-buildingGrade F70/100
- audit-prep-assistantGrade A100/100
- burpsuite-project-parserGrade A90/100
- c-reviewGrade A93/100
- cairo-vulnerability-scannerGrade A100/100
- chrome-mcp-troubleshootingGrade A90/100
- code-improverGrade A92/100
- code-maturity-assessorGrade A100/100
- constant-time-analysisGrade C71/100
- cosmos-vulnerability-scannerGrade A92/100
- devcontainer-setupGrade F75/100
FAQ
Questions
- Is agentic-actions-auditor safe to install?
- No critical findings, some security notes. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
- How was this score calculated?
- Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
- Is this report current?
- It was made from commit 5c99c03 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.
- I wrote this skill. Can I fix the score or have the page removed?
- Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.
Related
Keep reading
Free tool
Scan your own skill
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.