plan
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's "Library Documentation" step explicitly performs WebSearch ("WebSearch: "{library} {framework} integration 2026"") and fetches external docs via mcp__context7__query-docs, causing the agent to read and incorporate open/public third‑party web content into its plans.
Audit Metadata