skills/roentek/claude_code_boilerplate_framework/three-brain/Snyk

three-brain

Warn

Audited by Snyk on Sep 30, 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 workflow ingests outsider-authored videos or YouTube URLs via yt-dlp and processes them through ffmpeg and Gemini, exposing the agent to untrusted content.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 30, 2026, 10:48 AM

Issues

1