ClawHub

PLS Agent Tools

Security checks across malware telemetry and agentic risk

Overview

This skill is a visible command-reference utility with risky shell examples, but no hidden code, installer, persistence, credential access, or exfiltration target was found.

Install this only if you want the agent to have a broad shell-command reference. Before allowing commands that delete or move files, edit files in place, kill processes, download files, or send network requests, confirm the exact path, port, process name, URL, and expected effect.

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
92% confidence
Finding
The skill advertises itself with very broad triggers such as 'everyday labor' and 'utility functions for common operations,' making it likely to be invoked for many unrelated tasks. Because the skill includes file, process, and network capabilities, overbroad routing increases the chance that high-impact actions are suggested or used in contexts where they were not specifically requested or safety-checked.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill bundles destructive and system-affecting commands including deletion, in-place edits, forced process termination, downloads, and HTTP POST requests without prominent warnings, confirmation requirements, or scope restrictions. In an agent setting, this is dangerous because these examples normalize actions that can cause data loss, service interruption, or unintended data transmission if applied automatically or to user-supplied targets.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal