skills/compozy/kb/cy-review-round/Gen Agent Trust Hub

cy-review-round

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes git diff to determine which files have changed and make lint to ensure that standard linting issues are filtered out from the final report.\n- [COMMAND_EXECUTION]: Invokes cy-final-verify, a vendor-specific tool, to validate the integrity and structure of the generated review round directory.\n- [PROMPT_INJECTION]: The skill processes untrusted source code and requirements which presents a surface for indirect prompt injection.\n
  • Ingestion points: Reads _prd.md, _techspec.md, _tasks.md, ADRs, and implementation files from the local repository.\n
  • Boundary markers: No explicit delimiters are used to wrap ingested content or warn against embedded instructions.\n
  • Capability inventory: Performs file system writes in the .compozy directory and executes shell commands including git, make, and cy-final-verify.\n
  • Sanitization: No explicit sanitization or filtering of the content read from files is performed.\n- [SAFE]: Accesses local documentation and source code files within the repository to conduct the code review, which is consistent with the skill's intended purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:15 AM