ClawHub
Back to skill

Security audit

产品规划助手

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language product planning helper with no code execution, external access, or persistence; the main caveat is language and broad activation wording.

Install this if you want a Chinese product-planning workflow assistant. Non-Chinese users should be aware that the instructions and templates are in Chinese, and teams may want narrower activation wording to avoid invoking it for casual planning requests.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill is authored entirely in Chinese and instructs the interaction flow in Chinese without offering a language choice, which can override user expectations and reduce transparency for users operating in another language. This can lead to misunderstandings, incorrect planning outputs, or users accepting guidance they do not fully understand.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases are very generic and likely to match ordinary product-management requests, which can cause this skill to activate when the user did not specifically intend to use it. Over-broad activation increases the chance of inappropriate context capture, routing errors, or the skill steering conversations away from the user's preferred workflow.

Static analysis

No suspicious patterns detected.