rails-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted code from pull requests and diffs, creating an attack surface for instructions hidden within code comments or documentation.
- Ingestion points: SKILL.md instructs the agent to process
git diff,PR diff, and file contents provided in the context. - Boundary markers: The instructions do not include specific delimiters or warnings to the agent to ignore instructions that might be embedded within the content it is reviewing.
- Capability inventory: The skill contains no code scripts, tool configurations, or network operations, limiting the impact of any potential injection.
- Sanitization: No sanitization, filtering, or validation steps for the ingested code are defined.
Audit Metadata