ClawHub

self-check

Security checks across malware telemetry and agentic risk

Overview

This self-check skill inspects local OpenClaw setup details and API-key presence but only reports status and suggested fixes, with no evidence of hidden changes or data exfiltration.

Install this only if you want a local OpenClaw health check. Treat its report as potentially sensitive because it can reveal installed skills, enabled services, paths, permissions, and whether API keys are configured; review any suggested repair commands yourself before running them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill’s documented behavior explicitly involves reading environment variables, inspecting files and permissions, and invoking a Python script, which implies access to env, file_read, shell, and possibly network-dependent checks. Because these capabilities are not declared in permissions metadata, operators cannot accurately assess or constrain what the skill can access, creating a real transparency and least-privilege issue even if the stated purpose is legitimate self-diagnostics.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The self-check goes beyond environment integrity checks by enumerating environment variables and recursively inspecting config files for key/token/secret-like fields. Even though it does not print secret values, this still performs secret discovery and creates an inventory of sensitive material that is not clearly necessary for a diagnostic skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal