rolewire

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The agent retrieves job listings and descriptions from Rolewire, which indexes external company ATS platforms, representing low-risk search and retrieval of third-party content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs querying a third-party domain (rolewire.app) for search feeds and job details, and executing an npx package installation (rolewire-mcp@latest) from an unverified public registry, constituting an unknown/unverified operational external dependency.