ClawHub
Back to skill

Security audit

Agent Health Monitor

Security checks across malware telemetry and agentic risk

Overview

This skill mostly performs local agent health checks, but it also runs an undisclosed status script from another installed skill.

Review before installing. Use this only if you trust the local feishu-evolver-wrapper skill and are comfortable with this monitor reading OpenClaw session metadata and running local shell status checks; otherwise remove or disable the hard-coded wrapper status check.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
The skill invokes shell commands via execSync and directly runs another skill's lifecycle script using a shell-built command containing a filesystem path. Although the current path is derived from HOME and appears non-user-facing, this expands the skill's capability from passive health observation into command execution and cross-skill control/status inspection, increasing attack surface and creating command/path injection and trust-boundary risks if environment variables or workspace contents are manipulated.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger conditions are broad enough to activate on generic phrases like 'check agents' or whenever the system 'needs' monitoring, which can cause the skill to run outside a narrowly scoped health-monitoring request. Over-broad activation increases the chance of unnecessary status inspection, unintended access to operational data, or chaining into monitoring actions in contexts where the user did not explicitly request them.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
index.js:17