entity-audit

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly searches and ingests content from public third-party sources (Wikidata, Google Knowledge Panel, Wikipedia, and industry directories) and uses those untrusted/user-generated values to verify properties and drive remediation actions, so external content can influence subsequent decisions and tool use (see Process steps 2–5).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 01:03 PM