Brave Search
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
SKILL.md
text/markdown · 1273 字节
content.js
text/javascript · 2582 字节
package-lock.json
application/json · 20515 字节
package.json
application/json · 332 字节
search.js
text/javascript · 5329 字节
Security Scan
状态
suspicious
OpenClaw
gpt-5-mini
OpenClaw 分析
The skill's description and README claim a Brave Search API integration and an API key, but the shipped code actually scrapes Brave Search HTML and does not use any API key — that mismatch (plus an instruction to run npm ci) is inconsistent and worth asking the author or treating cautiously.
置信度: high
VirusTotal
Type: OpenClaw Skill Name: brave-search Version: 1.0.1 The OpenClaw AgentSkills bundle 'brave-search' is classified as benign. The `SKILL.md` provides clear, non-malicious instructions for web search and content extraction. The `search.js` and `content.js` scripts perform HTTP requests to `search.brave.com` and user-specified/search-result URLs, respectively, using standard web scraping and HTML parsing libraries. There is no evidence of intentional data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or obfuscation. The dependencies listed in `package.json` and `package-lock.json` are appropriate for the stated functionality.