wuying-browser-use

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). This skill spawns an automated browser and executes user-provided tasks that navigate and scrape arbitrary public websites (see SKILL.md examples like 京东, 新浪新闻, 微博) via scripts/browser-use.py's call to agent.browser.execute_task(args.task), so it ingests untrusted third‑party content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:30 AM