logs
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to run "vercel logs " and follow logs from arbitrary Vercel deployments, which pulls untrusted, user-generated runtime content (app logs) that the agent is expected to read and analyze.
Audit Metadata