browse
Warn
Audited by Snyk on Jul 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: 0.85). SKILL.md describes a runtime workflow that can open and snapshot arbitrary web pages (e.g.,
browse open <url>thenbrowse snapshot/browse get text body), which would ingest outsider-authored page text/DOM into the agent context via the browser inspection outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata