docx
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). The skill unpacks and processes arbitrary user-supplied .docx files (see scripts/unpack.py and related readers that extract and parse word/document.xml and other XML parts), so the agent will ingest and interpret untrusted third‑party document content.
Audit Metadata