animation-review

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: 0.90). The skill records and analyzes arbitrary web content and user videos — record_browser.py accepts any URL to browse/record and analyze.py accepts user-provided video files (or Playwright captures of public sites), which are then sent to Gemini for frame-level interpretation, so untrusted third-party or user-generated content can be ingested and influence the agent's outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:33 AM