high-fidelity-extraction

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: 1.00). The skill explicitly instructs the agent to scrape public social media platforms (Instagram, TikTok, YouTube) and extract captions, comments, and other user-generated content via browser automation/DOM analysis (see "extract deep intelligence from social media platforms" and the DOM/navigation instructions), which are untrusted third-party sources the agent will read and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:27 AM