ClawHub

Feature Task Planning

Security checks across malware telemetry and agentic risk

Overview

This appears to be a development-planning skill that may write a planning document, but the behavior is purpose-aligned and not high-impact.

Before installing, be aware that this skill may read project context and save a development planning markdown file in the repository. Use it when you want a persistent plan, and review the generated path and content before committing it.

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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger description includes broad intent phrases like '技术方案定了，接下来怎么开发' and '帮我拆一下开发计划', which can cause the skill to activate on loosely related planning requests. Over-broad activation increases the chance the agent enters a workflow that reads project files and produces repository changes when the user did not explicitly request this specific skill.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to generate and save a planning document into the repository without requiring an explicit user-facing notice at the time of the write. This creates a silent side effect on the codebase, which is risky because a user may believe they are only asking for analysis or advice, not authorizing persistent modification of repository files.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal