exa-search
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The configuration instructions recommend using
npxto download and execute theexa-mcp-serverpackage from the npm registry, which is a well-known service. - [PROMPT_INJECTION]: The skill processes untrusted content from the web through its search and crawling capabilities, creating a surface for indirect prompt injection.
- Ingestion points: Tools such as
web_search_exaandcrawling_exa(SKILL.md) ingest external data into the agent's context. - Boundary markers: None explicitly defined in the instructions for handling search results.
- Capability inventory: The skill provides search and content extraction capabilities; it does not explicitly define file-system or shell execution tools, though the agent environment may provide them.
- Sanitization: No specific sanitization or filtering instructions are provided for the ingested web content.
Audit Metadata