code-quality-review
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions explicitly state to 'Stay read-only' and only perform 'narrow read-only checks'. There are no indications of data exfiltration, external network requests, or commands that modify the system state.
- [PROMPT_INJECTION]: The skill processes untrusted input in the form of code diffs and local repository files. This creates a surface for indirect prompt injection where instructions hidden in code could attempt to manipulate the AI's review. However, the risk is mitigated by the read-only constraint and lack of high-privilege capabilities. * Ingestion points: The skill reads repository diffs and instructions from other local SKILL.md files. * Boundary markers: There are no specific delimiters used to separate user-controlled code from the agent's instructions. * Capability inventory: The skill is restricted to read-only repository analysis and does not have write or network access defined in its instructions. * Sanitization: No content filtering or input validation is specified for the code being reviewed.
Audit Metadata