Skills
skills/phy041/claude-agent-skills/exa-web-search-free/Gen Agent Trust Hub

exa-web-search-free

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configures a connection to Exa AI's official Model Context Protocol (MCP) endpoint at mcp.exa.ai to retrieve search tool definitions and capabilities.
  • [COMMAND_EXECUTION]: Utilizes the mcporter command-line interface to register MCP servers and invoke search functions such as web_search_exa and get_code_context_exa.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection as the skill retrieves and processes untrusted content from the public web, GitHub, and StackOverflow; the skill serves as a data ingestion point for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 07:23 PM