light-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git diffs, commit logs, and external specification or standards files. This ingestion creates a surface where malicious content within a pull request or repository file could attempt to influence the agent's behavior during the review process.
- Ingestion points: Data enters the context via git diff, git log, and files located in docs/, specs/, or .scratch/ as described in WORKFLOW.md.
- Boundary markers: The workflow provides some protection by requiring agents to use 'quoted hunks', specific field IDs (F-###), and citations to standards files, which helps separate data from instructions.
- Capability inventory: The skill's capabilities are limited to reading local files/git history and spawning sub-agents for parallel analysis. It does not possess network-access or file-writing tools, which significantly limits the potential impact of an injection.
- Sanitization: No specific sanitization or filtering of the diff content or logs is mentioned before processing.
Audit Metadata