Agentic Actions Auditor

- **Action Security Profiles:** See [{baseDir}/references/action-profiles.md]({baseDir}/references/action-profiles.md) for per-action security field documentation, default configurations, and dangerou...

Security View Source →

LLM Evaluation

Evaluated by: xiaomi/mimo-v2-flash:free

Last evaluated: March 29, 2026

Prompt Quality

3.0 /5

Evaluation error: RetryError[]

Usefulness

3.0 /5

Evaluation error: RetryError[]

Overall Rating

3.0 /5

Evaluation failed

Prompt Preview

---
name: agentic-actions-auditor
description: "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 c...

Full prompt length: 21542 characters

Tools & Technologies

• python
• ruby