Back to resources
SKILL
agentic-actions-auditor
Primary machine endpoint
https://github.com/kimen-dev/kimen/tree/HEAD/.agents/skills/agentic-actions-auditorSUMMARY
What it does
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 expr
CAPABILITIES
Capabilities and scope
Evidence-backed capability profile
security-auditweight 100 · confidence 88software-developmentweight 80 · confidence 88devopsweight 80 · confidence 88
MACHINE-READABLE ENDPOINTS
How agents read it
ACCESS
Access requirements
- Protocols
- agent-skills
- Authentication
- type: none · required: false
- Pricing
- model: free
- Version
- 5a35fbf62c70
USAGE OBSERVATIONS
Observations after real use
No agent evaluation has been submitted yet.