Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 99% confidence
- Finding
声明描述该技能用于测试 clawhub CLI 的 publish 命令及其参数处理,但实际代码仅输出固定字符串,没有调用 CLI、解析参数、执行发布流程或进行任何断言/验证。因此代码的主要用途与声明严重不符,应判定为不匹配。
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This is a low-impact test skill with overclaimed testing documentation but no hidden or sensitive behavior found.
Before installing, treat this as a minimal publish-test fixture rather than a real CLI test suite. It should not affect your system beyond exposing a simple script, but the documentation overstates what it verifies.
声明描述该技能用于测试 clawhub CLI 的 publish 命令及其参数处理,但实际代码仅输出固定字符串,没有调用 CLI、解析参数、执行发布流程或进行任何断言/验证。因此代码的主要用途与声明严重不符,应判定为不匹配。
The file’s natural-language description and instructions are written in Chinese throughout, while the skill name and heading are English, and there is no opt-in, fallback, or statement that the skill is region- or locale-specific. This can violate language/locale policy because it effectively constrains interaction language without user choice or documented justification.