futurepedia

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 tool pages from futurepedia.io via Unbrowse MCP, which exposes third-party content (AI tool descriptions and reviews) to the agent upon search or page retrieval.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill connects to a remote third-party MCP server hosted at unbrowse.ai, which provides behavior-defining instructions and tool execution, representing an unofficial external operational dependency with common/reputable provenance.