ClawHub
Back to skill

Security audit

Quirky Help

Security checks across malware telemetry and agentic risk

Overview

This troubleshooting skill is coherent and low-risk, but it may guide an agent to inspect screenshots, browser pages, or local files when those are relevant.

Installers should use this skill for concrete troubleshooting tasks and keep shared screenshots, browser sessions, files, and command output limited to the problem at hand. Confirm before allowing changes to settings, accounts, files, or system state.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is triggered by very broad conditions like screenshots, pasted errors, UI confusion, and setup blockers, which overlap with a large share of ordinary support conversations. That can cause over-invocation of the skill, expanding its access to screen-aware, browser, image, or local inspection behaviors in cases where a narrower skill or normal chat response would be safer and more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.