gha-security-review
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's core functionality involves analyzing untrusted GitHub Actions workflow files, which introduces an indirect prompt injection attack surface. A malicious workflow could contain instructions aimed at influencing the agent's audit findings or behavior.
- Ingestion points: The skill reads workflow files from .github/workflows/ and local action.yml files into the agent's context.
- Boundary markers: The process description does not include the use of delimiters or specific instructions to treat audited content as untrusted data.
- Capability inventory: The skill is configured with tools including Bash and WebFetch, which could be leveraged if an injection is successful.
- Sanitization: There is no documented mechanism for sanitizing or validating the content of audited files before they are processed by the agent.
Audit Metadata