agent-browser

Warn

Audited by Snyk on Jul 8, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime scraping workflow where the agent uses browser snapshot/DOM text extraction (e.g., “获取所有 n 级引用的文本内容”) from an arbitrary target URL, which is outsider-authored free text from public web pages.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 8, 2026, 04:47 PM
Issues
1
Security Audit — snyk — agent-browser