A skill for OpenClaw that verifies link validity, source credibility, and factual accuracy of online content.
v1.0.0链接与资讯真实性核验工具,检查链接是否可访问、交叉验证资讯真实性。
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The name/description and SKILL.md promise cross-source fact verification using web_search and web_fetch, but index.js only performs HEAD/GET requests and returns a page title; there is no search/cross-check implementation. This is a meaningful mismatch between claimed capability and actual code.
Instruction Scope
SKILL.md instructs the agent to use `web_fetch` and `web_search` to cross-verify content and to 'search multiple sources', but the runtime code does not call any search tool or implement cross-verification. The instructions are broader than what the code will do at runtime.
Install Mechanism
No install spec or external downloads; this is an instruction-only skill with a small local index.js. No high-risk install mechanism detected.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not ask for sensitive access.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent/system-wide privileges or modify other skills. Autonomous invocation is allowed by default but not combined with other red flags here.
What to consider before installing
The skill's documentation promises cross-source fact-checking but the code only checks whether a URL responds and extracts its <title>. Before installing or using it for verification: 1) don't trust it to perform cross-checks — ask the author or inspect/modify the code to actually call web_search and aggregate sources; 2) be aware the skill will fetch any URL you provide (so don't submit private links or links containing secrets); 3) the fetch timeout and HEAD behavior may not behave as expected in some runtimes — test with known URLs; 4) if you need real fact-checking, request/require an implementation that performs authenticated searches (if needed), documents which search endpoints are used, and shows how results are aggregated/weighted. If the mismatch was accidental, ask the publisher to update SKILL.md or the code to align functionality and provide provenance for its searches.Like a lobster shell, security has layers — review code before you run it.
latest
链接事实核验工具
功能
- 检查给出的URL是否可以正常访问
- 抓取资讯内容,核验资讯真实性
- 交叉对比多个来源确认事实
- 输出标准化核验结果
使用方式
- 用户给出需要核验的链接:直接访问并返回状态
- 用户给出资讯内容:搜索多个来源交叉验证
输出格式
【核验结果】
- 链接:URL
- 状态:可正常访问 / 无法访问 / 404 / 连接超时
- 资讯真实性:✅ 信息匹配 / ⚠️ 部分存疑 / ❌ 虚假信息
- 备注:简要说明
依赖
- 使用
web_fetch工具访问链接 - 使用
web_search搜索交叉验证
Comments
Loading comments...
