project-ci-failure-signatures
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for using the official GitHub CLI (gh) to perform diagnostic tasks like inspecting PR checks and viewing job logs. These activities are standard for development workflows and no malicious intent or suspicious command patterns were identified.
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it requires the agent to ingest and analyze untrusted output from CI logs. 1. Ingestion points: CI log content retrieved via
gh run view. 2. Boundary markers: Absent; the instructions do not implement delimiters to prevent the agent from following instructions potentially embedded in logs. 3. Capability inventory: The agent is authorized to useghcommands and perform workflow re-runs. 4. Sanitization: None; logs are processed directly without filtering. While this surface exists, it is intrinsic to the skill's primary purpose of log analysis, and the risk is considered low within this context.
Audit Metadata