code-review
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted code diffs and commit histories, which creates a potential surface for indirect instructions.
- Ingestion points: The skill loads branch diffs, changed files, and local project guidance documents like .cursor/rules/* and AGENTS.md in SKILL.md workflow steps 5 and 6.
- Capability inventory: The skill is restricted to file reads, git command execution (blame, diff), and spawning isolated sub-agents for review passes. It does not perform network operations or write to the filesystem.
- Boundary markers: The instructions lack explicit delimiting markers or warnings to the model to ignore natural language instructions that might be embedded within the code diffs.
- Sanitization: No input validation or filtering of the code content is specified before the diff is analyzed by the agent.
Audit Metadata