claude-agents
Warn
Audited by Snyk on Feb 17, 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 lists WebSearch and WebFetch as tools for the "Researcher" archetype and in the "Common patterns" tool configurations, which means agents built from this skill may fetch and read open/public web content (untrusted third-party sources) as part of their workflow.
Audit Metadata