vercel-react-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's metadata claims the author is "vercel" and states it is maintained by "Vercel Engineering", whereas the platform identifies the account author as "charlie85270". While this is an attribution discrepancy, the content itself consists of legitimate developer guidelines and does not contain malicious instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill is intended to be used by an agent to review or refactor user-supplied React and Next.js code, which introduces an attack surface for indirect prompt injection.\n
- Ingestion points: User-provided source code files are processed during performance audits and refactoring tasks as specified in SKILL.md.\n
- Boundary markers: There are no specific instructions or delimiters provided to prevent the agent from following instructions potentially embedded within the user's code.\n
- Capability inventory: The skill is intended for use with coding assistants that typically possess file system read/write access and shell execution capabilities.\n
- Sanitization: No mechanism for sanitizing or validating the ingested code content is specified within the skill instructions.
Audit Metadata