an2b-warden-governanceEvaluates and governs all OpenClaw bot actions using YAML policies with tamper-evident audit logs to allow, deny, or require review before execution.
Install via ClawdBot CLI:
clawdbot install jcools1977/an2b-warden-governanceGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://mandeldb.com/api/v1/portal/registerPotentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://getsentinelos.comAudited Apr 17, 2026 · audit v1.0
Generated Mar 3, 2026
Ensures AI agents handling patient data comply with HIPAA by blocking unauthorized access and requiring review for sensitive actions like data deletion. It logs all actions to a tamper-evident audit trail for compliance audits.
Governs AI agents in banking or fintech by reviewing payment creation and blocking risky actions like code execution in production. It uses built-in policy packs to enforce safety and monitor API calls for fraud detection.
Prevents accidental or malicious email deletion by requiring human review for email.delete actions. It monitors all email-related activities and logs them to a hash chain for security investigations.
Manages AI agents in DevOps pipelines by blocking shell.execute and code.execute in production environments. It enforces YAML policies to ensure only approved actions run, reducing operational risks.
Governs AI-powered support bots by monitoring message.send and file.write actions to prevent data exfiltration. It uses community mode with local policies for cost-effective governance without external dependencies.
Offers a free community version with local YAML policies and SQLite audit, while charging for enterprise features like Sentinel_OS cloud governance, EngramPort memory, and compliance exports. Revenue comes from subscription tiers based on usage and support.
Provides professional services to design and implement custom YAML policies, integrate with existing systems, and train teams on governance best practices. Revenue is generated through project-based fees and ongoing support contracts.
Sells pre-built policy packs (e.g., basic_safety, phi_guard) through a marketplace, allowing users to quickly deploy governance for specific use cases. Revenue comes from one-time purchases or licensing fees for premium packs.
💬 Integration Tip
Start with community mode using local YAML policies to test governance without API keys, then gradually integrate enterprise features like Sentinel_OS for advanced monitoring and EngramPort for cloud memory.
Scored Jun 1, 2026
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
全面排查企业的经营风险情况,适用于供应商准入尽调、贷前风险筛查、合作伙伴背景调查等场景,全方位预警潜在经营风险,辅助决策者规避合作隐患。
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
Audit and score OpenClaw AgentSkills against structural compliance, quality standards, and OpenClaw-specific architecture patterns. Produces a 0-100 score wi...