cy-review-round

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard local development commands such as git diff for change discovery and make lint for code quality filtering. It also references a local verification utility, cy-final-verify. These operations are consistent with the tool's purpose as a code review and auditing assistant.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content from the repository, including source code, PRDs, and technical specs. This provides a surface for indirect prompt injection where maliciously crafted content could attempt to influence the agent's logic.
  • Ingestion points: The agent reads various implementation files and documentation from the .compozy/tasks/ directory and the wider repository (SKILL.md, Steps 2 and 3).
  • Boundary markers: None explicitly defined; the instructions direct the agent to read the full content of the files.
  • Capability inventory: Includes the ability to read and write files within the project structure and execute local shell commands like make and git.
  • Sanitization: There is no mention of sanitizing or validating the content read from the repository files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:15 AM