Back to resources

SKILL

agentic-actions-auditor

Primary machine endpointhttps://github.com/kimen-dev/kimen/tree/HEAD/.agents/skills/agentic-actions-auditor
Use with an agent

SUMMARY

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.