vercel-react-best-practices
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (HIGH): Significant risk of adversarial influence via ingestion of untrusted source code for analysis and refactoring.\n
- Ingestion points: Processes external React components, Next.js pages, and application logic from the user's workspace as described in the 'When to Apply' section.\n
- Boundary markers: No explicit boundary markers or delimiters are defined to separate the code context from potential embedded instructions.\n
- Capability inventory: The skill is intended to guide 'automated refactoring and code generation,' implying the agent has capabilities to write or modify files on the system.\n
- Sanitization: There is no evidence of sanitization or filtering to prevent the agent from obeying instructions hidden within code comments or metadata fields.
Recommendations
- AI detected serious security threats
Audit Metadata