ClawHub
Back to skill

Security audit

Clickup

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ClickUp task-tracking workflow, but users should be mindful that it can store work details in an external service.

Install this only if you want your agent to manage ClickUp task records during normal work. Avoid putting secrets, credentials, personal data, regulated data, or confidential project details in task names or descriptions unless you explicitly intend to store them in ClickUp, and inspect the local cu/cu.cjs helper before relying on it.

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
95% confidence
Finding
The skill description instructs use whenever the user asks for something non-trivial or after any meaningful action, which is an unusually broad trigger for writing to an external SaaS system. In practice, this can cause the agent to persist user requests, project details, and intermediate work artifacts to ClickUp without clear user consent or data-minimization checks.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill encourages storing task descriptions, completed work, and future ideas in an external ClickUp workspace but does not warn that prompts, project context, bug details, or user information may be sensitive. This omission raises the risk of accidental data exfiltration to a third-party service, especially because the workflow says to log meaningful work by default.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.