no-explicit-any
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs analysis on external, untrusted TypeScript files, which could contain instructions or patterns designed to mislead or influence the agent's analysis results.\n
- Ingestion points: The skill ingests and reviews TypeScript files provided in the session context as part of the code review process.\n
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to prevent the agent from acting on content found within the code files.\n
- Capability inventory: The agent is authorized to scan files, report issues, and suggest code modifications (e.g., replacing code with Zod validation or unknown types).\n
- Sanitization: No sanitization or content filtering is applied to the analyzed files before the agent processes them.
Audit Metadata