requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: LOW
Full Analysis
- [COMMAND_EXECUTION] (SAFE): Uses standard git commands (git rev-parse, git log) to retrieve commit hashes for the review process. These are local, read-only operations.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill acts as a template for sending data to a subagent. It ingests implementation details and plans (SKILL.md) which could potentially contain adversarial instructions, but the skill itself lacks high-privilege capabilities that would lead to a compromise.
Audit Metadata