ClawHub
Back to skill

Security audit

Collaboration Helper

Security checks across malware telemetry and agentic risk

Overview

This appears to be a local task-tracking skill that stores tasks in a JSON file, with no artifact-backed evidence of exfiltration, deception, or unsafe persistence.

Before installing, confirm you are comfortable with the skill creating or updating its local JSON task file. If you use a custom data path, choose a dedicated task file rather than pointing it at unrelated workspace or sensitive files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documentation advertises shell execution plus file read/write behavior, but no permissions are declared. That creates a trust and containment gap: a caller or review system may assume the skill is low-risk while it can persist data and operate on the filesystem, including an arbitrary workspace path. In this context, persistent task storage and alternate workspace access make the undeclared capabilities more concerning, because they enable modification or inspection of files outside the skill’s own directory.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.