github-actions-author

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected where the skill processes untrusted local data.\n
  • Ingestion points: Reads existing workflow files in .github/workflows/, package.json, and lockfiles from the repository (SKILL.md).\n
  • Boundary markers: Lacks explicit boundary markers or instructions to ignore embedded directives in the ingested files.\n
  • Capability inventory: The skill has the capability to write and modify GitHub Actions workflow files.\n
  • Sanitization: No explicit content validation or sanitization is performed on the ingested file data before processing.\n- [COMMAND_EXECUTION]: Performs local shell operations and GitHub CLI queries to manage workflows and check dependencies.\n
  • Evidence: Uses gh workflow list, gh release view, and git status to retrieve repository metadata and action version tags.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — github-actions-author