document-extraction
Warn
Audited by Snyk on Mar 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Yes — the SKILL.md explicitly shows "Parse Remote URLs" (client.parse with document_url) and "Extract from URL" / "Split from URL" examples that fetch and ingest arbitrary public web pages/URLs, which the agent reads and uses to drive classification and extraction decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata