yutori-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: 0.90). This skill uses run_browsing_task with a user-provided start_url to navigate and extract data from arbitrary public websites, exposing the agent to untrusted third‑party web content that could carry indirect prompt injection.
Audit Metadata