exa-web-search-free

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configures a connection to Exa AI's official Model Context Protocol (MCP) endpoint at https://mcp.exa.ai/mcp. This is a well-known service for neural search.
  • [INDIRECT_PROMPT_INJECTION]: The skill has the capability to ingest untrusted data from the web through its search and crawling tools.
  • Ingestion points: Data enters the agent's context through the web_search_exa, get_code_context_exa, and crawling_exa tools as described in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are provided in the skill instructions.
  • Capability inventory: The skill uses the mcporter command-line tool to perform network-based search operations.
  • Sanitization: No explicit sanitization or filtering of search results is performed by the skill itself; the agent relies on its own internal safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:03 PM
Security Audit — agent-trust-hub — exa-web-search-free