ClawHub
Back to skill

Security audit

AI时代职业诊断

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language career risk diagnostic skill that asks for job details and generates a local Markdown report, with no executable code or network behavior.

Before installing, expect the skill to ask about your job, experience, income mix, skills, and career worries, then create a local Markdown report. Avoid including details you do not want saved, or ask the agent to show the report inline or omit sensitive fields before writing a file.

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)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs the agent to write a Markdown report file containing sensitive career and financial details, including job role, years of experience, income structure, skills, and anxieties, without any consent, minimization, retention, or privacy warning. This creates a real privacy risk because personal data may be persisted to disk unexpectedly, exposed to other users/processes, or retained longer than the user intended.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The skill's visible display name is hard-coded in Chinese ("AI 职业风险诊断") with no indication that users can choose another language or locale. This creates a natural-language policy concern because the skill presents a fixed language experience without documented opt-in or justification.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
The description, trigger phrases, and output expectations are all presented in Chinese, and the skill does not indicate that users may choose another language. This can be a language-policy issue when a skill implicitly forces one language without opt-in or justification.

Static analysis

No suspicious patterns detected.