Skywork Document
Warn
Audited by Snyk on Mar 20, 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). The skill explicitly states in SKILL.md ("Web Search Built-In
- The Doc API automatically performs web searches on demand to gather up-to-date content") and the create_doc.py SSE handling (e.g., "deepsearch"/content_chunk events) that the server will fetch and use open web content as part of document generation, meaning untrusted third‑party pages can be ingested and materially influence generation/next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata