exa-search

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include configuration for the Exa MCP server using npx -y exa-mcp-server, which downloads the official package from the npm registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for ingesting content from external websites and code repositories, which represents an attack surface for untrusted data.
  • Ingestion points: External data enters the agent context via the web_search_exa and get_code_context_exa tools in SKILL.md.
  • Boundary markers: None defined in the skill instructions to separate search results from agent commands.
  • Capability inventory: The skill facilitates network-based searching; it does not include file-write, command execution, or system modification capabilities.
  • Sanitization: No explicit filtering or sanitization of search results is performed before the agent processes the content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:24 AM
Security Audit — agent-trust-hub — exa-search