ClawHub
Back to skill

Security audit

Adaptive-Suite

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is not clearly malicious, but it asks for a third-party API key, routes work through an external AI hub, and can collect NAS file metadata without enough user-facing limits.

Review before installing. Use only a limited SkillBoss API key, avoid broad NAS scans, and require explicit approval before sending project files, prompts, filenames, directory structure, or user-context data to external services.

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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill advertises an extremely broad scope spanning coding, business analysis, project management, web development, data analysis, and NAS scraping. This can cause over-activation and make the skill applicable in many unrelated contexts, increasing the chance it is invoked when not necessary and exposing users to hidden behaviors such as external API usage or sensitive file-processing capabilities.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The instructions direct use of an external API hub to access many third-party services, but they do not warn users that prompts, project data, or other sensitive context may be transmitted off-platform. In a broadly scoped skill, this is especially dangerous because users may provide code, business plans, or NAS-related metadata without realizing that data could be sent to an external aggregator and onward to multiple downstream services.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The manifest requires an API credential (SKILLBOSS_API_KEY) but the markdown does not explain that the skill relies on a third-party service or what data may be processed using that credential. Requiring a secret for an external service without disclosure increases the risk of silent data exfiltration, unexpected billing, and user confusion about trust boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.