agent-arch-system-design
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 allows a "WebSearch" tool for researching patterns (allowed_tools: WebSearch) and thus can fetch and read open/public web content as part of its workflow, exposing the agent to untrusted third-party material that could carry indirect prompt injections.
Audit Metadata