github
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates a high degree of security maturity, providing detailed instructions for auditing GitHub Actions workflows for vulnerabilities. It correctly advocates for industry best practices such as least-privilege permissions, OIDC authentication, and SHA-pinning of dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill provides the agent with access to potentially untrusted data from GitHub issue reports, pull request descriptions, and CI logs. It effectively mitigates the risk of the agent executing malicious instructions embedded in this data through explicit core rules (e.g., Rule 20) and documentation that defines the attack surface and required defensive posture.
- [PROMPT_INJECTION]: A static detector flag in
references/issues-and-triage.mdregarding instruction overrides was evaluated as a false positive. The text is part of a technical reference explaining how to detect and handle malicious input from external users, rather than an attempt to subvert the agent's own safety guidelines.
Audit Metadata