agent-capability-matrix
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). This skill explicitly lists and instructs agents to use a "WebSearch" tool (see reference/matrix-table.md and the Research/Selection Flowchart entries) for framework/market/company research, which entails fetching and interpreting open/public web content (untrusted/user-generated) as part of its workflow.
Audit Metadata