NYC

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 directly ingests and processes arbitrary user-supplied .docx files (see "Reading/Analyzing Content" — the pandoc conversion command under "Text extraction" and the ooxml/scripts/unpack.py unpacking/raw XML access) so the agent will read and interpret untrusted user-generated document content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:50 AM