ClawHub
Back to skill

Security audit

AI Prompt 工具箱

Security checks for vulnerabilities and agentic risk

Overview

This is a content-only prompt template skill with broad Chinese-language prompt guidance, but no hidden execution, persistence, credential access, or data exfiltration behavior was found.

Install this if you want a Chinese prompt-template toolbox. Be aware it may shape answers for many writing, coding, analysis, translation, and business requests, and the package appears less complete than advertised because the referenced prompts.md file is not included. Avoid putting private or sensitive information into generated prompts unless needed.

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
  • 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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description is extremely broad, covering writing, coding, analysis, translation, and business use cases. Such a wide activation surface can cause the skill to trigger on many ordinary user requests, increasing the chance it overrides more appropriate system behavior or injects its prompt-selection workflow into unrelated conversations.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill description and instructions are entirely in Chinese and present the interaction model as if Chinese is the required language, with no user-facing option to choose another language. This can violate language/locale policy expectations when a skill implicitly forces a specific language without opt-in.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The usage instructions say that whenever the user needs a prompt for a scenario, the skill will recommend a template, but they do not specify a strict trigger or user consent mechanism. This ambiguity makes accidental activation more likely, which can lead to prompt hijacking of normal requests and unintended influence over the assistant's response style or content.

Static analysis

No suspicious patterns detected.