docx

Warn

Audited by Snyk on Feb 15, 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 explicitly unpacks and parses arbitrary user-supplied .docx files (see ooxml/scripts/unpack.py and scripts/document.py which read and operate on word/document.xml, and the pandoc-based text-extraction workflow), so the agent ingests and interprets untrusted user-generated document content at runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:37 PM