v2ex
Warn
Audited by Snyk on Sep 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The agent searches and reads pages on v2ex.com via search queries and URL/path navigation, making outsider-authored forum content low-risk per the scoring guidelines.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to connect to an external remote MCP server hosted at unbrowse.ai, which provides operational behavior-selecting tools and configuration, and unbrowse.ai is an unofficial third-party provenance.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata