ClawHub
Back to skill

Security audit

Task Prism

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only planning skill that gives project decomposition templates and does not request code execution, credentials, network access, or persistent privileges.

Install this if you want Chinese-language project planning and task decomposition templates. Be aware it may activate for broad planning requests and may be less suitable for users expecting multilingual behavior, but it does not appear to add sensitive permissions or unsafe actions.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

High
Confidence
94% confidence
Finding
The skill declares very broad trigger phrases such as '帮我拆解任务', '做个项目计划', and '任务怎么分工', and also claims it should trigger across any industry. That can cause the skill to activate on loosely related requests, overriding more appropriate domain-specific skills or injecting heavyweight planning behavior where the user did not intend it. In an agent setting, overbroad activation expands the skill’s influence surface and can lead to misrouting, unnecessary data exposure to the skill context, or degraded safety controls from more specialized handlers.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill metadata and content are written to operate in Chinese and imply Chinese-language responses without checking the user’s language preference. This is primarily a safety/usability issue: forcing a language can cause misunderstanding of requirements, incorrect plans, or user confusion, especially for multilingual or cross-border contexts where precise interpretation matters. The surrounding context slightly increases concern because the skill is intended for project planning and cross-cultural scenarios, where language mismatch can materially distort outputs.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The examples file is entirely in Chinese and does not indicate any user language selection logic or a documented locale constraint. In a general-purpose task decomposition skill, this can exclude or mislead users who interact in other languages, causing incorrect understanding of requirements and degraded usability, though it is not a direct code-execution or data-exfiltration risk.

Static analysis

No suspicious patterns detected.