ClawHub
Back to skill

Security audit

Adaptive Suite

Security checks across malware telemetry and agentic risk

Overview

This skill is not clearly harmful, but it combines broad work access, an external API key, NAS file metadata scanning, and vague learning behavior without enough privacy and control boundaries.

Review before installing. Use it only if you are comfortable providing a SkillBoss API key, can restrict NAS scans to explicit non-sensitive paths, and can prevent sensitive project data, filenames, credentials, or business context from being sent to the external API or retained for later use.

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
91% confidence
Finding
The manifest describes a very broad, multi-domain skill with user-invocable access but no explicit scope boundaries, approval gates, or data-handling limits. This increases the chance the agent will be used for sensitive tasks outside the author's intended safety envelope, leading to overreach, unsafe automation, or misuse of connected tools and credentials.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly directs use of an external API endpoint and declares an environment-based API key requirement, but it does not warn users that task content or metadata may be transmitted off-platform. In a user-invocable skill, this can result in unanticipated disclosure of prompts, project data, filenames, or other sensitive context to a third party.

Ssd 3

Medium
Confidence
90% confidence
Finding
The instruction to 'continuously learn from user interactions' implies persistence or reuse of user-provided information beyond the immediate session, but the skill provides no retention limits, consent model, or privacy controls. This creates a risk of unauthorized storage, profiling, or later leakage of sensitive user or project information.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal