review-agent
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of code diffs and pull request descriptions, creating a surface for indirect prompt injection attacks.
- Ingestion points: The agent is instructed to read external pull request descriptions and code diffs to understand and verify changes (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or 'ignore embedded instructions' warnings to help the agent distinguish its core logic from the untrusted content being reviewed.
- Capability inventory: The skill directs the agent to 'Run the tests and the linter' (SKILL.md), which involves executing code that may be part of the untrusted diff being analyzed.
- Sanitization: No sanitization or validation of the input code is specified before the agent executes tests or linting tools.
Audit Metadata