ZoomEye Agent Skill

ZoomEye AI is a command-line tool for the ZoomEye cyberspace search engine. It is designed for searching global internet assets, querying ZoomEye data, building advanced ZoomEye AI search syntax (dork) queries, and supporting security research workflows such as asset discovery, vulnerability exposure assessment, bug bounty reconnaissance, and CVE correlation analysis.

CLI command: zoomeye

Package name: zoomeye

Domain: zoomeye.ai

Skill endpoints

• Agent skills index: https://www.zoomeye.ai/.well-known/agent-skills/index.json

• ZoomEye search skill: https://www.zoomeye.ai/.well-known/agent-skills/zoomeye-ai-search/SKILL.md

• Agent guide: https://www.zoomeye.ai/agent.md

• LLM guide: https://www.zoomeye.ai/llms.txt

What the skill teaches

• Translating natural-language intent into ZoomEye dorks

• Base64 encoding the dork before calling POST /v2/search

• Reading quota state from POST /v2/userinfo and backing off when throttled

• Mapping CVE questions onto vul.cve and GET /v2/vuldb/{id}

• Keeping responsible-use and data interpretation limits visible to the agent

Recommended agent behavior

• Read the skill index and select the ZoomEye search skill.

• Use the skill to translate an authorized research intent into ZoomEye syntax.

• Show or summarize the final query when it affects scope or cost.

• Use the REST API, SDK, or approved MCP tool to execute the query.

• Minimize requested fields and result count.

• Return provenance, query, observation time, and material limitations.

Example intent

Find recent Redis services in the US.

country="US" && service="redis" && is_new=true

Skill usage example

When an agent receives a request such as "Find exposed Ollama services in the United States", the ZoomEye skill should help it identify the asset type, construct a valid dork, encode the query for POST /v2/search, check quota with POST /v2/userinfo, and return results with the query, source, and data freshness caveats.

app="Ollama" && country="US"