vercel-composition-patterns
Fail
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Deceptive metadata detected in SKILL.md. The author field is set to 'vercel', a recognized trusted organization, which contradicts the actual skill author Mrziadd0. This identity impersonation is a form of metadata poisoning designed to misguide safety evaluations and project trust.
Recommendations
- AI detected serious security threats
Audit Metadata