ClawHub
Back to skill

Security audit

weeek-tasks

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward WEEEK task-management helper that uses a user-provided token to read and change WEEEK tasks.

Install this only if you want an agent to access your WEEEK account through your API token and modify tasks. Keep WEEEK_TOKEN private, use the narrowest token permissions available, and review create, update, complete, uncomplete, or move commands before running them in a shared workspace.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly relies on environment variables and network access to call the WEEEK API, but it does not declare those capabilities. Undeclared sensitive capabilities reduce transparency and can bypass expected review or consent controls, especially because the skill can access credentials and perform remote actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation describes commands that create, update, complete, and move tasks in a remote third-party system without any warning that these operations make persistent external changes. This increases the risk of unintended modifications if an agent or user invokes the skill without clear confirmation semantics.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill instructs users to set an authorization token but gives no guidance on secure handling of that credential. This can lead to accidental token exposure through shell history, logs, screenshots, or improper storage, which would allow unauthorized access to the user's WEEEK account.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
This script exposes commands that create, update, complete, and move tasks immediately against a live remote API without any confirmation prompt, dry-run mode, or safety interlock. In an agent setting, that increases the risk of unintended destructive or integrity-impacting actions from misunderstood prompts, prompt injection, or simple operator error.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.