process-guardMonitor critical processes and auto-restart on failure. Tracks CPU and memory usage, escalates alerts via webhook, callback, or file, and writes a dead man's...
Install via ClawdBot CLI:
clawdbot install theshadowrose/process-guardGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
webhook → https://hooks.slack.com/services/...Potentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
http://localhost:11434/api/tagsUses known external API (expected, informational)
slack.comGenerated Mar 20, 2026
Ensures critical web servers and microservices remain operational by automatically restarting failed processes. Monitors CPU/memory usage to prevent resource exhaustion and provides real-time status via HTTP dashboard for DevOps teams.
Maintains uptime for data collection agents and gateway services in manufacturing environments. Uses TCP port checks to verify connectivity and escalates alerts via webhooks when critical processes fail, minimizing production downtime.
Monitors algorithmic trading engines and market data feeds with configurable health checks. Auto-restarts failed processes within seconds to maintain trading continuity and writes heartbeat files for external compliance monitoring.
Ensures continuous operation of patient data pipelines and HL7 interface engines. Uses shell command checks to verify service health and implements command allowlists to maintain security compliance in regulated environments.
Keeps video encoding and content delivery processes running 24/7. Monitors resource usage to prevent overloads during peak traffic and provides JSON status endpoints for integration with existing monitoring dashboards.
Offer basic monitoring and auto-restart functionality as free open-source software. Charge for enterprise features like advanced alert escalation, SLA guarantees, and premium support services to larger organizations.
Provide ProcessGuard as a cloud-managed service with centralized dashboard and multi-instance management. Include automated configuration, 24/7 monitoring support, and integration with popular DevOps tools for monthly recurring revenue.
Offer professional services to implement ProcessGuard within client infrastructure. Provide custom health check development, alert system integration, and training services alongside the core software package.
💬 Integration Tip
Start with simple HTTP checks for web services before implementing complex shell commands. Use the dead man's switch heartbeat file to integrate with existing monitoring systems like Nagios or Prometheus.
Scored Apr 19, 2026
AI Analysis
The skill's external API usage (webhooks, local health checks) is consistent with its stated monitoring and alerting purpose. The 'UNSAFE_SHELL' signal appears to be an example command ('rm -rf /') used for illustration, not a hidden instruction. No evidence of credential harvesting, data exfiltration, or obfuscation was found in the provided definition.
Audited Apr 16, 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.
Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.
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.
577+ pattern prompt injection defense. Now with typo-tolerant bypass detection. TieredPatternLoader fully operational. Drop-in defense for any LLM application.
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.