skills/unbrowse-ai/sites/futurepedia/Gen Agent Trust Hub

futurepedia

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill provides instructions and metadata for connecting to a remote MCP server but does not include any local scripts or executable code.
  • [EXTERNAL_DOWNLOADS]: The skill references connection points and documentation on the vendor's official domain (unbrowse.ai). These are documented as standard configuration for the service.
  • [INDIRECT_PROMPT_INJECTION]: As a tool that fetches data from an external website (futurepedia.io), the skill has an ingestion surface for untrusted content. However, this is the primary purpose of the skill, and the provided tools are read-only search and retrieval functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:12 AM