exa-web-search-free
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted external sources, including general web pages, GitHub repositories, and Stack Overflow discussions, which could contain instructions designed to manipulate the agent's behavior.
- Ingestion points: External content is retrieved using the
web_search_exa,get_code_context_exa,company_research_exa, andcrawling_exatools defined inSKILL.md. - Boundary markers: Absent; there are no specific instructions or delimiters provided to help the agent distinguish between search results and legitimate instructions.
- Capability inventory: The skill has the ability to perform web searches, extract code context, and crawl specific URLs through the
mcportercommand-line interface. - Sanitization: Absent; the skill does not implement filtering or sanitization of the retrieved content to remove potential injection patterns before processing.
- [COMMAND_EXECUTION]: The skill relies on the
mcportercommand-line utility to interact with the Exa search tools and manage configuration. - [EXTERNAL_DOWNLOADS]: The skill fetches search results and web content from Exa's official MCP endpoint at
https://mcp.exa.ai/mcp.
Audit Metadata