verify-pr-logs
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or behaviors were detected. The skill follows security best practices for AI agents, particularly regarding the handling of untrusted external data.
- [INDIRECT_PROMPT_INJECTION]: The skill recognizes that CI logs are an attack surface for indirect prompt injection and provides explicit defensive instructions to mitigate this risk.
- Ingestion points: Untrusted data enters the agent context when fetching logs via
gh run view --log-failedorgh run view --loginSKILL.md. - Boundary markers: The instructions explicitly define boundaries by telling the agent to ignore narrative text and focus solely on structured patterns like file paths and error codes.
- Capability inventory: The skill has capabilities to modify the file system (Step 6) and execute build/test commands (
npm test,ghCLI), which are necessary for its primary purpose. - Sanitization: The skill mandates a "diagnosis-first" approach, requiring the agent to explain the root cause to the user before implementing any changes, ensuring a human-in-the-loop verification step.
Audit Metadata