drawio-diagrams-enhanced
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 instructs the agent to load and use external public libraries and templates via URLs (e.g., https://jgraph.github.io/drawio-libs/... and app.diagrams.net) and to call get_diagram to retrieve user-edited XML, which clearly causes the agent to fetch and read untrusted third‑party content as part of its workflow.
Audit Metadata