research-to-diagram
Warn
Audited by Snyk on Aug 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In this skill’s runtime workflow, user-submitted research topics trigger “multi-round WebSearch” where the agent collects and extracts knowledge from web results, ingesting outsider-authored free text from the web at analysis time.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata