yutori-browse
Warn
Audited by Snyk on Apr 11, 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). The SKILL.md explicitly instructs using run_browsing_task with a user-provided start_url to browse and interact with arbitrary public websites, meaning the agent will fetch and interpret untrusted third-party web content that could contain malicious/indirect instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata