browser-automation

Warn

Audited by Snyk on Jun 21, 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). The skill’s required workflow uses agent-browser open <url> and subsequent snapshot/click/fill, which at runtime can ingest arbitrary public web page text (outsider-authored) into the agent’s LLM context via browser-extracted DOM/content.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 21, 2026, 01:43 AM
Issues
1
Security Audit — snyk — browser-automation