visual-qa

Warn

Audited by Snyk on Mar 10, 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 explicitly navigates to and captures public website content (see SKILL.md pages list like https://csrdevelopment.com/... and the screenshot.py which accepts --url and run_all_pages builds URLs from a base_url and PAGES), causing the agent to read and analyze untrusted third‑party web pages whose content can materially influence analysis and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:39 AM