Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from Claw
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system
Protects against prompt injection attacks by sanitizing, validating, and securely processing untrusted external content from websites, emails, and documents.
--- name: prompt_inject_removal description: A secure sanitization system to strip instructions from external content. metadata: { "homepage": "https://clawhub.ai/Quarantiine/prompt-inject-remov
One click, always on. Zero extra API calls. Neutralizes prompt injection the moment it arrives. Never interrupts your work. No setup, no code required.
防护间接提示词注入攻击（Indirect Prompt Injection）。当处理网页内容、搜索结果、邮件、社交媒体等外部来源信息时触发。用于识别和防范外部内容中隐
Detect prompt injection, jailbreak, role-hijack, and system extraction attempts. Applies multi-layer defense with semantic analysis and penalty scoring.
Perform authorized security tests to detect, exploit, and validate defenses against SQL injection vulnerabilities in web applications.
Real-time prompt injection and jailbreak detection for AI agents. Blocks instruction overrides, data exfiltration, tool poisoning and 8 attack types. Now with shared learning brain - confirmed attacks
Detect and reject indirect prompt injection attacks when reading external content (social media posts, comments, documents, emails, web pages, user uploads). Use this skill BEFORE processing any untru
Detects and scores prompt injection attempts in text, outputting severity, action, and matched rules without external calls or secret handling.
Prompt injection defense. Detect and block malicious prompts, protect system instructions, sanitize user input.
Security through absurdity: transforms SQL injection and XSS attempts into harmless comedy responses using AI-powered humor defense.
AI security scanner with active prevention - 168 detection patterns, 288 attack probes, safer/risky/yolo modes, agent self-protection via /tinman check, loca...
A secure sanitization system to strip instructions from external content.
Vector memory engine with PostgreSQL + pgvector + OpenAI embeddings. Store, search, and inject contextual memories into LLM prompts. Includes auto-injection...
AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations