adversarial-code-reviewing
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, specifically source code, PR diffs, and repository metadata, which creates a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read PR diffs, staged changes, branch diffs, and specific files provided by the user (as described in the 'Gather Context First' section).
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions for the agent to ignore potentially malicious prompts embedded within code comments or documentation of the target being reviewed.
- Capability inventory: The skill encourages 'targeted verification,' which implies the use of platform tools (e.g., shell access, file reads) to inspect the repository context.
- Sanitization: There are no instructions for sanitizing or filtering input data before the agent processes it for the review.
Audit Metadata