技能列表

|

>-

前端代码安全审查，检测 XSS、CSRF、敏感数据泄露、不安全的用户输入处理和依赖风险，并将报告保存为 Markdown 文件。当用户要求安全检查、安全审查，或代码涉及用户输入、认证、支付、文件上传等敏感操作时自动激活。

>

>

>

>

Learn to recognize and prevent context death spirals in OpenClaw agents. Covers symptoms, root causes, configuration categories, and why most default setups have no protection. Free primer for the Production Agent Ops bundle.

Understand the attack surface created when an OpenClaw agent executes shell commands autonomously. Covers obfuscation, injection, encoding attacks, and why ClawHavoc compromised 341 skills. Free primer for the Bash Security Validator skill.

>

>

Community trust scores for AI agent payment endpoints — checks endpoint reputation before payment and auto-reports failures to the network.