hallucination-detector

Warn

Audited by Snyk on Mar 8, 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 explicitly fetches and parses public third-party resources as part of its required workflow—e.g., verifyPackageExists queries the public npm registry at https://registry.npmjs.org/... and verifyAPIEndpoint references external API docs URLs (Step 5)—meaning untrusted, user-supplied web content is ingested and can change validation/blocking decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 01:09 PM