exa-search
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
83
86%
Does it follow best practices?
Impact
98%
7.00xAverage score across 2 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Yes—this skill’s required workflow uses Exa MCP tools (e.g., `web_search_exa`, `get_code_context_exa`, `crawling_exa`) to fetch and extract outsider-authored web/code content at runtime, which is then provided to the agent/LLM as readable text (indirect prompt-injection risk).
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill requires running "npx exa-mcp-server" at runtime (see SKILL.md), which will fetch and execute the exa-mcp-server package from the npm registry (e.g. https://www.npmjs.com/package/exa-mcp-server), so remote code is fetched-and-run and the service controls search/synthesis used by the agent.
- Repository
- affaan-m/ECC
- Commit
754b8dd
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.