code-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze external code, creating an entry point for untrusted data.
- Ingestion points: User-provided source code and configuration files processed during the review workflow as described in the response approach (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or warnings to treat processed code as untrusted data, relying on the model's inherent safety filters.
- Capability inventory: No active capabilities such as file-system writes, network operations, or shell execution are defined within the skill instructions or metadata.
- Sanitization: No input validation or sanitization routines are specified for the ingested content before processing.
Audit Metadata