Home / Skills / agentic-actions-auditor

agentic-actions-auditor

security

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

License
CC-BY-SA-4.0
SKILL.md tokens
5,435
Bundled files
14
Bundled tokens (estimated)
19,494

Cost per 1,000 loads

Estimated input cost per 1,000 loads of SKILL.md only (characters ÷ 4). Bundled files, output tokens and execution are excluded.

ModelInput / 1M tokens1,000 loads
Claude Opus 5$5.00$27.18
Claude Sonnet 5$2.00$10.87
Claude Haiku 4.5$1.00$5.43
Anthropic pricing source

Safety flags

Detected automatically from files; not a security audit.

Runs scripts
No
Network access
Yes
Shell commands
No

Works with

Open SKILL.md format

  • Claude Code
  • Codex
  • Cursor
  • GitHub Copilot
  • Gemini CLI
  • OpenCode
  • Goose

Install

npx skills add trailofbits/skills --skill agentic-actions-auditor

Last verified:

agentic-actions-auditor FAQ

What does the agentic-actions-auditor skill do?

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 Source: https://github.com/trailofbits/skills/blob/main/plugins/agentic-actions-auditor/skills/agentic-actions-auditor/SKILL.md

What does the agentic-actions-auditor skill cost to load?

SKILL.md is about 5,435 tokens. Estimated input cost per 1,000 loads: Claude Opus 5 $27.18; Claude Sonnet 5 $10.87; Claude Haiku 4.5 $5.43. Estimated input cost per 1,000 loads of SKILL.md only (characters ÷ 4). Bundled files, output tokens and execution are excluded. Prices: https://docs.anthropic.com/en/docs/about-claude/pricing

How do I install the agentic-actions-auditor skill?

Skills CLI: npx skills add trailofbits/skills --skill agentic-actions-auditor. Claude Code: /plugin marketplace add trailofbits/skills, then install the plugin from that marketplace. Download the agentic-actions-auditor skill folder as a ZIP and upload it in Claude.ai skills settings.

Is the agentic-actions-auditor skill safe?

Automatically detected flags: network access. Flags are detected automatically from the skill's files and are not a security audit; review the SKILL.md before installing.

Related security skills

All skillsAll security skills

My AI Stack