react-best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill description and body attribute the content to 'Vercel Engineering'; however, the repository and author ('sickn33') are community-based and unverified. This mismatch in provenance could lead to a false sense of trust regarding the official nature and safety of the instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to have the agent write, review, and refactor React/Next.js code, which involves processing untrusted external data.
- Ingestion points: Source code files provided by the user for review or optimization as described in the 'When to Apply' section of SKILL.md.
- Boundary markers: The skill does not define any delimiters or specific instructions to isolate the guidelines from potentially malicious instructions embedded in the code being analyzed.
- Capability inventory: The skill directs the agent to perform code generation, refactoring, and file modification tasks.
- Sanitization: The skill contains no instructions for the agent to sanitize, escape, or validate external content before processing it.
Audit Metadata