web-research
Warn
Audited by Snyk on Feb 16, 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 explicitly uses a WebSearch tool and a WebFetch step to retrieve and read web pages and public websites (news, product pages, technical docs) from the open web, exposing the agent to untrusted third‑party content that it will parse and interpret.
Audit Metadata