vercel
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt tells users to "provide [the Protection Bypass secret] to you" and includes curl/header and URL examples that require embedding the secret verbatim, so the agent would need to accept and output secrets directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to access and interact with Vercel preview deployments (e.g., https://your-preview-url.vercel.app) — user-provided public URLs whose content is untrusted and which the agent is expected to read/interpret (including using bypass headers/query params), enabling potential indirect prompt injection.
Audit Metadata