exa-web-search-free

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow uses Exa search/crawling tools (e.g., web_search_exa, get_code_context_exa, and optional crawling_exa) to ingest arbitrary free text content returned from outsider-authored sources based on user-supplied queries/URLs, enabling indirect prompt injection via results/pages read by the LLM.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs mcporter to add and use a remote MCP endpoint (https://mcp.exa.ai/mcp and https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,deep_search_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check) which mcporter will fetch at runtime to load tool definitions that can directly control agent prompts/behavior and are required for the skill to function.