review-quality-change
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code changes, which introduces a potential attack surface where instructions embedded in data could attempt to influence agent behavior. \n
- Ingestion points: The skill analyzes a "supplied change scope" for review (SKILL.md). \n
- Boundary markers: The instructions do not define specific markers or warnings to isolate processed data from the agent's system instructions. \n
- Capability inventory: The skill has no defined capabilities; it does not perform file writes, network requests, or command execution, and has no associated tools. \n
- Sanitization: There are no instructions for sanitizing or filtering input code before processing. \n- [NO_CODE]: The skill consists entirely of natural language instructions and metadata. No scripts, binaries, or package dependencies are included.
Audit Metadata