data-extractor
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s workflow is document-content extraction (PDF/Word/HTML/email/etc.) where the runtime ingests the provided document’s body text (outsider-authored if the user supplies documents/comments from others) into the agent/LLM context via extracted
element.text/chunks.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata