document-extraction

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). This skill ingests arbitrary web content (e.g., "Web Page | URL" in Supported Document Types, the document_assessment path "{file path or URL}", and competitor analysis prompts that record "source URL") via a WebFetch-style tool, so the agent would read untrusted third-party webpages that could contain injected instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:20 AM