academic-paper
Warn
Audited by Snyk on Aug 27, 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’s Phase 1 “Extract from user input” saves and then drives the rest of the pipeline (via
_workspace/00_input.mdand subsequent inter-agent processing), so outsider-authored free text is directly ingested at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata