ClawHub
Back to skill

Security audit

Api Model list updater

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it helps users fetch model lists from configured providers and add selected models to OpenClaw configuration.

Install only if you want a tool that can read your OpenClaw provider configuration, contact selected provider model-list endpoints using configured credentials, and edit your OpenClaw model settings. Prefer the slash command, verify the config path, and keep the generated backup so changes can be reversed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The natural-language triggers are broad phrases like 'show me available models' and 'what models are on lmstudio', which could plausibly appear in ordinary conversation and unintentionally invoke a skill that reads configuration, contacts external services, and writes to disk. Because this skill performs side effects, accidental activation materially increases risk beyond a harmless informational action.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script sends authenticated requests to provider-controlled endpoints and then modifies the user's OpenClaw configuration, but it does not clearly warn the user beforehand that secrets may be used for outbound network calls and that local config will be rewritten. In a skill/agent context, this reduces informed consent and makes it easier for a misconfigured or malicious provider entry to trigger unexpected external requests and persistent configuration changes.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.