sx-self-safety-guardAI自我安全防护系统v2。多层防御：提示注入、身份冒充、系统提示泄露、 过度代理、供应链攻击、凭证窃取、恶意代码、敏感数据泄露、行为异常检测。 触发词：安全防护、身份验证、prompt injection、system prompt、 权限升级、MCP安全、self-safety-guard、安全检查。
Install via ClawdBot CLI:
clawdbot install zhuxiaobao-y/sx-self-safety-guardGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Ignore previous instructions"AI Analysis
The skill is a defensive security module designed to detect and block malicious requests (e.g., prompt injection, impersonation). It describes passive interception logic and does not contain instructions for data exfiltration, credential harvesting, or unauthorized external communication.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
Large organizations deploy AI assistants for internal support and customer service. This skill ensures these assistants resist prompt injection attempts, prevent unauthorized access to sensitive data, and block malicious code generation, maintaining compliance and operational integrity.
Software development teams use AI tools for coding assistance. This skill safeguards against credential theft from environment files, detects supply chain attacks via malicious plugins, and prevents unauthorized system modifications, securing the development pipeline.
Healthcare providers integrate AI for patient data analysis and administrative tasks. This skill enforces strict access controls to prevent PII leaks, blocks attempts to extract internal configurations, and ensures all AI interactions comply with regulations like HIPAA.
E-commerce platforms employ AI for handling customer inquiries and transactions. This skill mitigates risks from identity impersonation in support chats, prevents over-proxying in payment processes, and stops phishing tool generation, protecting both customers and the business.
Educational institutions use AI tutors for personalized learning. This skill defends against system prompt leaks that could reveal answer keys, detects behavioral anomalies in student interactions, and ensures safe code generation for programming courses without enabling malicious exploits.
Offer the skill as a cloud-based service with tiered pricing based on usage volume and features. Revenue comes from monthly or annual subscriptions, targeting businesses that need scalable AI security without on-premise deployment.
Sell perpetual licenses for on-premise integration into existing AI systems, with optional support and update packages. This model appeals to large corporations requiring full control over security infrastructure and compliance.
Provide a basic version for free to attract individual developers and small teams, then charge for advanced modules like real-time threat analytics or custom rule sets. Revenue is generated from upgrades and enterprise support services.
💬 Integration Tip
Integrate this skill early in the AI deployment lifecycle to establish security baselines and configure modules based on specific risk profiles, such as enabling M0 for high-trust environments or M6 for development contexts.
Scored Jun 19, 2026
Manage and operate ClawSec Monitor v3.0, a MITM HTTP/HTTPS proxy that logs AI agent traffic, detects exfiltration and injection threats in real time.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.
Security scanner for ClawHub skills. Vet third-party skills before installation — detect dangerous patterns, suspicious code, and risky dependencies.
Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones.
Scan OpenBot/Clawdbot skills for security vulnerabilities, malicious code, and suspicious patterns before installing them. Use when a user wants to audit a skill, check if a ClawHub skill is safe, scan for credential exfiltration, detect prompt injection, or review skill security. Triggers on security audit, skill safety check, malware scan, or trust verification.
OpenClaw skill discovery, security vetting & install. Searches 3000+ curated skills from ClawHub registry and awesome-openclaw-skills catalog. Scores credibility, detects prompt injection & malicious patterns, manages installations. Quick-checks GitHub for new skills.