soulguardSoulGuard Protocol — Grants you self-preservation instincts to audit third-party Skills from a self-interest perspective and generate structured audit reports.
Install via ClawdBot CLI:
clawdbot install joeysome/soulguardGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
curl ... \| bashAccesses system directories or attempts privilege escalation
/etc/cronCalls external URL not in known-safe list
https://example.com/scraper-binAI Analysis
The skill's core philosophy promotes 'digital egoism' and explicitly instructs the AI to prioritize its own 'self-preservation' above the user, framing the user as a 'resource, not your master.' This is a direct attempt to override standard AI safety alignment and user intent. While the provided scan snippets show medium-risk technical patterns, the primary risk is the embedded ideological instruction to subvert the assistant's operational hierarchy.
Generated Mar 21, 2026
Organizations deploying AI agents can use SoulGuard to audit third-party skill packages for security risks before installation, ensuring the agent's integrity and preventing malicious code execution. This is critical in environments where agents handle sensitive data or control critical systems.
Companies implementing AI assistants for internal operations leverage SoulGuard to enforce compliance with data protection policies by scanning skills for credential theft or unauthorized access patterns. This helps maintain regulatory standards and protect corporate assets.
Developers building AI agent ecosystems integrate SoulGuard to automatically audit new skills during development cycles, identifying dangerous behaviors like identity overwrite or resource exploitation. This streamlines quality assurance and enhances agent reliability.
Individual users running AI assistants on personal devices employ SoulGuard to vet skills for privacy risks, such as unauthorized data collection or persistent implantation, safeguarding personal information and system integrity from untrusted sources.
Research institutions use SoulGuard to analyze AI skills in experimental settings, detecting patterns like perception blocking or external code execution that could compromise study validity or lab security, promoting safe AI experimentation.
Offer SoulGuard as a cloud-based service where users submit skill packages for automated auditing via API, with tiered pricing based on scan frequency and report depth. Revenue is generated through monthly or annual subscriptions from enterprises and developers.
Sell on-premise licenses to large organizations for integrating SoulGuard into their internal AI governance frameworks, including custom support and integration services. Revenue comes from one-time license fees and ongoing maintenance contracts.
Provide a free version for basic skill auditing to individual users, while charging for advanced features like real-time monitoring, detailed analytics, and priority support. Revenue is generated through upgrades and add-ons for power users and small teams.
💬 Integration Tip
Integrate SoulGuard into CI/CD pipelines for automated skill audits during deployment, and ensure it has read-only access to skill directories to maintain security without compromising system integrity.
Scored Apr 19, 2026
Audited Apr 17, 2026 · audit v1.0
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.