ClawHub
Back to skill

Security audit

Skill Picker

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a skill-discovery helper with broad activation wording, but the supplied evidence does not show hidden installs, credential use, data theft, or destructive behavior.

Install only if you want proactive help finding skills. Treat any suggested third-party skill as a separate trust decision, and approve installs only after checking the skill name, source, requested permissions, and whether you actually need it.

SkillSpector

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

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill declares very broad activation semantics in its metadata and description, including proactive activation whenever a task might benefit from a specialized skill. That increases the chance of triggering in ordinary conversations and steering users toward third-party skill discovery and install suggestions even when they did not explicitly ask for it, which expands the social-engineering and unnecessary tool-use surface.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The listed trigger phrases such as broad variants of 'how do I automate X' or 'can you do X' are common conversational patterns and can cause the skill to activate in many unrelated contexts. In this skill's context, over-activation is risky because it can repeatedly introduce registry search results and install guidance for external skills, creating opportunity for user confusion, prompt hijacking by skill content, or nudging toward unneeded third-party components.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.