browse

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: 1.00). This skill's run_browsing_task accepts a user-provided start_url and navigates/scrapes arbitrary public websites, causing the agent to ingest untrusted third-party (public/web user-generated) content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:01 AM