diagnose-ci-failures
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources.\n
- Ingestion points: GitHub Actions logs are fetched via
gh run view <run-id> --log-failed(SKILL.md).\n - Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are provided to separate log content from instructions.\n
- Capability inventory: The skill uses
ghfor read operations. Although the skill itself is read-only, the agent environment may include tools for code modification or command execution that could be targeted.\n - Sanitization: No log sanitization or filtering is performed before processing.\n- [COMMAND_EXECUTION]: The skill utilizes the
gh(GitHub CLI) tool to perform its primary function.\n - Evidence: Commands include
gh run view,gh run list, andgh pr viewto fetch workflow and pull request information.
Audit Metadata