research

Warn

Audited by Snyk on Feb 19, 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's Wave 1 template and deployment rules explicitly require using "WebSearch" and citing URLs (Wave 1 Template: "Use WebSearch for current information. Include dates on all facts. Cite sources with URLs") and Quick Research Mode mentions "WebSearch + WebFetch on key URLs", so agents fetch and read untrusted public web content which is then synthesized to drive recommendations and decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 08:46 AM