drawio-generator
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: 0.70). The skill's workflow explicitly states it will read and extract entities from user-provided files (PDF, DOCX, TXT, MD), which are untrusted user-generated inputs the agent will ingest and interpret as part of its processing, creating an avenue for indirect prompt injection.
Audit Metadata