diagnose-ci-failures
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses git and the GitHub CLI (gh) to query current branch names, check PR statuses, and fetch CI run logs. These operations are standard developer tasks and are consistent with the skill's stated purpose of diagnosing build failures.
- [PROMPT_INJECTION]: Analyzed the surface for indirect prompt injection (Category 8) related to the ingestion of external CI logs.
- Ingestion points: External data enters the agent context via the gh run view command in SKILL.md.
- Boundary markers: Absent. The instructions do not define specific delimiters for separating log content from instructions.
- Capability inventory: The agent has access to shell commands via git and gh.
- Sanitization: No explicit sanitization or filtering of the log output is performed before analysis.
Audit Metadata