react-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's metadata and description claim that it is 'maintained by Vercel' and authored by 'vercel', whereas the providing account is 'tech-leads-club'. While the README acknowledges the original source, the platform-level metadata provides a misleading claim about the current maintainer.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to process project source code for refactoring and performance review, creating a surface for indirect prompt injection.
- Ingestion points: Project source files, React components, and Next.js pages are ingested into the agent's context (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external code as untrusted or to ignore embedded instructions within processed data.
- Capability inventory: The skill is intended for automated refactoring, code generation, and performance reviews (SKILL.md).
- Sanitization: No sanitization, escaping, or validation of user-provided code is implemented in the guidelines.
Audit Metadata