security-review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted content from local source code and git diffs, representing a potential injection surface.\n
- Ingestion points: Code changes are ingested via 'git diff' and file read operations as defined in the 'Review Workflow' section of SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters or isolation markers (e.g., XML tags) to separate analyzed code from the agent's instructions.\n
- Capability inventory: The skill is primarily diagnostic and lacks capabilities for network exfiltration, file system modification, or command execution beyond the 'git' utility.\n
- Sanitization: No sanitization of the input code is specified before it is processed by the agent.
Audit Metadata