claude-code-agent-patterns
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: 0.80). The skill explicitly includes a "Web-Focused" tool assignment listing WebFetch and WebSearch for "External information retrieval," which indicates the agent may fetch and read open/public third‑party web content (arbitrary URLs) as part of its workflow.
Audit Metadata