Content Repurposing
Warn
Audited by Snyk on Aug 23, 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). The skill only ingests a user-provided “source asset” (a link, transcript, or draft) supplied in Step 1 and then rewrites/extracts nucleus moments from that provided text, so outsider-authored free text is ingested without a trusted-provider restriction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata