browser-automation

Warn

Audited by Snyk on Feb 15, 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 explicitly supports web-scraping and agentic browser control (see "web-scraping", "browser automation", and references to "scrapers" and "agentic browser control" in SKILL.md), meaning the agent would fetch and read content from public websites and user-generated sources, exposing it to untrusted third-party content that could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:17 PM