NYC

genealogical-documentation

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: 0.80). The skill explicitly permits the agent (when the user requests research execution) to perform web_search and load/interpret public third‑party sites and databases—naming FamilySearch/wiki, Ancestry, Newspapers.com and county/state pages—so it will ingest untrusted/user‑generated web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:03 PM