ClawHub
Back to skill

Security audit

Self-Check Enhanced

Security checks across malware telemetry and agentic risk

Overview

This is a local OpenClaw diagnostic skill that checks system health and reports issues without modifying files or sending data out.

Install only if you want a local OpenClaw health-check tool. Review its output before sharing it, because it can reveal which services, logs, paths, backups, permissions, and API keys are present even though it does not display secret values.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill declares no explicit permissions, yet its documented behavior and execution path require access to environment variables, filesystem contents, shell commands, and likely network-relevant process inspection. This mismatch weakens security review and consent boundaries because a caller may invoke a broadly capable diagnostic skill without visibility into what resources it will inspect.

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
The self-check script inspects whether sensitive API credentials exist in environment variables and recursively scans configuration files for key/token/secret-like fields. Even though it does not print secret values, enumerating credential presence expands the script's access to sensitive material beyond basic health checks and can leak security posture or normalize unnecessary secret handling.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The invocation criteria are very broad (e.g., general troubleshooting, post-update checks, periodic health checks), so the skill could be triggered in routine conversations where the user did not intend a deep system inspection. Because this skill inspects configs, tokens, permissions, logs, and workspace state, overbroad activation increases the chance of unnecessary access to sensitive local data.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.