ClawHub

Auto Model Switch

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it can automatically switch OpenClaw models, but users should understand that this may change gateway configuration when a gateway token is provided.

Install only if you want a skill that can change the active OpenClaw model. Review config.yaml, use a least-privilege gateway token if possible, keep the token out of shared logs or files, and only enable heartbeat automation if automatic model changes are acceptable in your environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
72% confidence
Finding
This code can perform authenticated configuration changes against the gateway automatically, changing the active model without explicit user confirmation at the time of action. In environments where the gateway controls shared or sensitive inference settings, unauthorized or surprising reconfiguration could disrupt service, alter billing behavior, or route workloads to less-trusted models.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "龙虾小队",
  "license": "MIT",
  "dependencies": {
    "js-yaml": "^4.1.0"
  }
}
Confidence
90% confidence
Finding
"js-yaml": "^4.1.0"

Known Vulnerable Dependency: js-yaml==4.1.0 — 1 advisory(ies): CVE-2025-64718 (js-yaml has prototype pollution in merge (<<))

Low
Category
Supply Chain
Confidence
97% confidence
Finding
js-yaml==4.1.0

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal