security-review
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides developer guidelines and security best practices for handling authentication, user input, and sensitive data. It uses illustrative examples to contrast insecure practices (like hardcoding secrets) with secure implementations (using environment variables and parameterized queries).
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing external data, which introduces a theoretical surface for instructions embedded in data to influence the agent.
- Ingestion points: User-provided source code, API definitions, and configuration files provided in the agent's context for review (SKILL.md).
- Boundary markers: The skill does not define specific delimiters for separating user-provided code from the agent's instructions, relying on standard agent context boundaries.
- Capability inventory: The skill itself does not invoke shell commands, perform network operations, or write to the file system.
- Sanitization: The instructions specifically mandate the use of strict input validation (Zod) and HTML sanitization (DOMPurify) as critical security controls for any software under review.
Audit Metadata