skills/affaan-m/ecc/exa-search/Gen Agent Trust Hub

exa-search

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to install and configure the exa-mcp-server package from the NPM registry using npx. This is a standard requirement for utilizing Exa's neural search capabilities within the agent environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to search and retrieve content from the live web and public code repositories via the web_search_exa and get_code_context_exa tools, creating an attack surface for instructions embedded in external data.
  • Ingestion points: Data enters the agent context through search results and code documentation snippets retrieved via the Exa API.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the content returned by the tools.
  • Capability inventory: The skill facilitates broad read access to web content, including code examples and technical documentation.
  • Sanitization: No evidence of sanitization or filtering of the retrieved web content is present in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 02:13 PM
Security Audit — agent-trust-hub — exa-search