github-actions

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from the local repository, creating an attack surface for indirect prompt injection.
  • Ingestion points: The skill reads .github/workflows/*.yml files for auditing and project manifests (e.g., package.json, go.mod, requirements.txt, Cargo.toml) for project detection.
  • Boundary markers: None. No delimiters or instructions are used to separate untrusted file content from agent instructions.
  • Capability inventory: The skill uses Write and Edit tools and can execute GitHub CLI commands via Bash(gh:*).
  • Sanitization: Content from audited files is not sanitized before being used in CLI commands or generated reports.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:06 AM
Security Audit — agent-trust-hub — github-actions