recipe-review
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a high-level orchestrator for development tasks. It identifies local design documents and code changes using standard, non-privileged shell commands (
ls,git diff). - [SAFE]: Sub-agent interactions are well-structured, passing information between specialized tools (
code-reviewer,security-reviewer,task-executor) through defined JSON reports and prompts. No unauthorized data access or network exfiltration was detected. - [SAFE]: The skill includes manual review checkpoints (Step 4) where users must approve the execution of fixes, ensuring human oversight of automated modifications.
Audit Metadata