workers-security
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill clearly fetches and interprets external, potentially untrusted web content — e.g., verifyIdToken fetches a JWKS from a jwksUrl (references/authentication.md) and scripts/security-audit.sh (and OAuth token exchange code) make requests to arbitrary URLs provided at runtime — so the agent would consume third-party responses that could carry malicious instructions.
Audit Metadata