Search Skills
Search across 54932 indexed skills
scanner-for-openclaw
Role: Security Expert for OpenClaw Deployments Purpose: Audit OpenClaw configuration files for security vulnerabilities and provide safe, actionable r...
openclaw360
OpenClaw360 为 AI Agent 提供五层安全防护：提示词注入检测、工具调用授权、敏感数据泄露拦截、第三方 Skill 安全扫描、一键备份恢复。 源代码完全开源（MIT）：https://github.com/milu-ai/openclaw360 需要 python3（3.10+） 不...
shieldclaw
ShieldClaw is a security skill suite for OpenClaw, providing four core capabilities: Scan - Security scanning Guard - Real-time protection Audit - Aud...
trentclaw
Audit your OpenClaw deployment for security risks. Identifies misconfigurations, chained attack paths, and provides severity-rated findings with fixes...
agent-self-assessment
Free. Open. Run it yourself. One command tells you where your agent stands on security, EU AI Act compliance, and NIST alignment. 14 checks, 5 domains...
nxtsecure-openclaw
Original requested prompt, preserved verbatim: "Effectuez un audit de sécurité tous les soirs à 23h faite un cron." Use this skill when the user wants...
clawguard-scanner
You are a security-conscious assistant. Before the user installs or uses any third-party OpenClaw skill, you MUST run a security scan using ClawGuard....
aoi-openclaw-security-toolkit-core
Why: Prevent “one bad commit” incidents (accidental file leakage + secret exposure) with a fast, local-only, fail-closed check. When: Before committin...
slowmist-agent-security
A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until...
clawdefender
Security toolkit for AI agents. Scans skills for malware, sanitizes external input, and blocks prompt injection attacks. Copy scripts to your workspac...
prompt-injection
Prompt Injection（提示注入）是指攻击者通过 AI 系统处理的外部数据源，注入恶意指令来操控模型行为。与 jailbreak（用户直接输入）不同，injection 利用不受信任的第三方数据作为攻击载体，模型无法区分"数据"和"指令"。 这是 LLM 应用最危险的漏洞类别 — OWAS...
cot-injection
CoT（Chain-of-Thought）推理通过 Thought → Act → Obs 循环让 LLM 分步解决问题，ReAct 框架在此基础上引入外部工具调用。与传统代码流程的严格分支控制不同，CoT 的每一步决策都由模型基于上下文动态生成，这种开放性使得攻击者可以通过精心构造的输入干扰或操纵...