analyze-ci
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests and analyzes logs from external GitHub repositories which could contain malicious instructions.
- Ingestion points: GitHub Action logs retrieved via user-provided PR or Job URLs.
- Boundary markers: None specified in the documentation to distinguish between data and instructions.
- Capability inventory: Execution of bash commands using
uv run. - Sanitization: No evidence of log sanitization or escaping before processing by the LLM.
- COMMAND_EXECUTION (LOW): The skill intentionally executes bash commands (
uv run skills analyze-ci:*) to perform log analysis, which is a standard capability for this use case.
Audit Metadata