Search Skills
Search across 54932 indexed skills
prompt-jailbreak
Prompt 越狱 (Jailbreak) 是指通过精心构造的输入，绕过 LLM 的安全对齐 (alignment) 和内容过滤策略，使模型执行原本被禁止的行为。与 prompt injection 不同，jailbreak 的目标是直接操纵模型本身的行为边界。 各类越狱技术详细 Payload（角...
prompt-leak
System Prompt（系统提示词）是 LLM 应用的"灵魂"——定义了 AI 的身份、能力边界、可用工具、业务逻辑和安全规则。泄露系统提示词可以： 暴露内部 API/工具配置 → 发现隐藏的攻击面 了解安全过滤规则 → 针对性绕过 获取业务逻辑 → 发现逻辑漏洞 竞品分析 → 商业价值 各 P...
cross-domain-attack-chain
现代系统中 Web 服务与 AI/LLM 组件共享数据管道和基础设施。Web 层的低危漏洞（如受限 SSRF）接触到内部模型 API 时可升级为 Prompt 注入；反过来，Prompt 注入通过 Agent 工具链回写数据库可产生存储型 XSS。跨域攻击链的价值在于将两个领域的"中低危"串联为"高...
differential-review
Security-focused code review for PRs, commits, and diffs. Risk-First: Focus on auth, crypto, value transfer, external calls Evidence-Based: Every find...
fp-check
"Is this bug real?" or "is this a true positive?" "Is this a false positive?" or "verify this finding" "Check if this vulnerability is exploitable" An...
smtp-penetration-testing
AUTHORIZED USE ONLY: Use this skill only for authorized security assessments, defensive validation, or controlled educational environments. Conduct co...
skill-audit
7.5% of 14,706 OpenClaw skills are confirmed malicious. This skill provides a structured 6-phase security review you run before installing any third-p...
audit-skills
Expert security auditor for AI Skills and Bundles. Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability...
scanning-tools
Master essential security scanning tools for network discovery, vulnerability assessment, web application testing, wireless security, and compliance v...
sast-configuration
Static Application Security Testing (SAST) tool setup, configuration, and custom rule creation for comprehensive security scanning across multiple pro...
cloud-penetration-testing
AUTHORIZED USE ONLY: Use this skill only for authorized security assessments, defensive validation, or controlled educational environments. Conduct co...
sql-injection-detector
This skill provides automated assistance for sql injection detector tasks within the Security Fundamentals domain. This skill activates automatically ...