vendor-verification
Warn
Audited by Snyk on Jun 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill queries the public Wikidata API at runtime and ingests the returned free-text fields (e.g.,
description,label) into the generated markdown/JSON, which is outsider-authored web content; this is then written to.agents/workspace/vendor_verification_report.mdand.agents/workspace/vendor_verification_data.jsonfor downstream LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata