code-review-dangerous-sinks
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted source code (PHP, Python, JavaScript, Java, Ruby, Go, .NET/C#) which provides an attack surface for instructions embedded in data to influence the agent.
- Ingestion points: Source code files processed during code review as described in the skill.
- Boundary markers: No specific delimiters are defined to separate code content from instructions.
- Capability inventory: The skill leverages external tools like ripgrep and semgrep to search through files.
- Sanitization: The instructions do not specify any validation or sanitization of the source code content before it is processed by the agent.
Audit Metadata