five-axis-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external content, specifically code, diffs, and pull requests.
- Ingestion points: The agent processes user-provided code and diffs based on the instructions in
SKILL.md. - Boundary markers: The instructions do not specify delimiters or explicit instructions to ignore embedded commands within the code under review.
- Capability inventory: The skill contains no scripts, executable code, or tool invocations; its output is restricted to text-based commentary.
- Sanitization: No sanitization or filtering logic is present for the input data.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected. The skill primarily serves as a set of logical guidelines for the agent to follow during text-based code analysis.
Audit Metadata