Skills
skills/aradotso/mcp-skills/anysearch-mcp-server/Gen Agent Trust Hub

anysearch-mcp-server

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions recommend using npx to download and execute the mcp-remote and supergateway packages to enable specific transport modes for the search server.- [PROMPT_INJECTION]: The extract tool allows the agent to fetch and process content from arbitrary third-party URLs, which introduces a surface for indirect prompt injection.
  • Ingestion points: extract tool (SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: search, batch_search, extract (SKILL.md)
  • Sanitization: Not specified
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 10:19 PM
Security Audit — agent-trust-hub — anysearch-mcp-server