cy-review-round
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted data from the repository during the review process.\n
- Ingestion points: The skill reads source code identified through
git diff, requirements documentation in_prd.mdand_techspec.md, task definitions in_tasks.md, and architectural decision records in.compozy/tasks/<name>/adrs/.\n - Boundary markers: There are no instructions to use delimiters or specific ignore patterns to distinguish between the content being reviewed and the agent's operational instructions.\n
- Capability inventory: The skill performs shell command execution (
git diff,make lint,cy-final-verify) and local filesystem write operations for report generation.\n - Sanitization: No mechanisms for validating or escaping the content read from external files are specified before processing.
Audit Metadata