nuget

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

• Third-party content exposure detected (low risk: 0.10). The skill searches public package listings on nuget.org via user-initiated queries, fetching package descriptions and metadata authored by third parties.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures and connects to a remote third-party Model Context Protocol server hosted at https://unbrowse.ai/mcp/nuget.org, which acts as an operational runtime dependency with unverified first-party publisher provenance, placing it in the medium tier.