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_exaandget_code_context_exatools inSKILL.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