敏感研究目标或内部 URL 可能被发送给托管 Firecrawl
原文依据:5 处技能要求从用户消息、文件、URL 和上下文推断输入,并通过 Firecrawl 收集网页证据。若使用托管服务,请求中的 URL、搜索词、公司或人物目标会离开本地环境。
如果用户提供未公开的内部地址、保密项目名称、客户名单或调查对象,第三方服务可能接收到这些信息;本材料没有说明其保留、日志或再利用政策。
该技能明确要求使用 Firecrawl CLI 或同等工具收集网页证据,并声明托管请求需要 API 密钥。它还让代理从用户消息和上下文推断 URL、公司或主题。因此,在选用托管 Firecrawl 时,研究目标、查询词及待抓取 URL 可能被发送给第三方服务;若其中包含未公开的内部地址或敏感目标,会产生信息披露风险。不过,源码没有要求上传任意文件内容,也不能证明数据已被发送。用户可要求作者说明托管服务会接收和保留哪些字段,并限制为公开 URL、明确批准的查询及最小必要上下文。
inputs: - name: FIRECRAWL_API_KEY description: Firecrawl API key for hosted Firecrawl requests when the workflow runs through the CLI or API. required: truereferences:查看另外 4 个位置
Infer the workflow, inputs, audience, and output format from the user's request and surrounding context. If enough is clear, start immediately.1. Confirm the workflow and final artifact.2. Collect web evidence with Firecrawl through the CLI or equivalent Firecrawl tool surface.3. Save or cite source evidence so the final claims are traceable.4. Run independent research units in parallel when available.Do not run a long interview by default. First infer from the user's message, files, URLs, and surrounding context. If the agent can safely start, start.Ask at most 1-3 concise clarifying questions only when a required input is missing or ambiguity would materially change the work. Prefer defaults for non-blocking choices and state them briefly.- the URL, company, topic, or source to analyze- the desired deliverable or output format- a constraint that would materially change the workflow