skills/anthropics/claude-agent-sdk-demos/docx/Snyk

docx

Warn

Audited by Snyk on Sep 16, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to read, edit, and analyze local Word documents (.docx files) provided by the user, which may contain arbitrary text input.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 16, 2026, 12:34 PM

Issues

1