ClawHub
Back to skill

Security audit

Finance Capability Model

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language reference skill that generates a structured finance capability model and does not request risky access or perform actions.

Install this if you want a Chinese-language finance capability model reference or JSON template. Be aware that its trigger words are fairly broad, so it may be selected during some general finance, HR, or capability-model conversations.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger keywords are very generic terms related to finance, capability models, and talent assessment, so the skill may be invoked in many ordinary conversations that are not actually requesting this specialized output. This can cause unintended activation, response confusion, or inappropriate routing in multi-skill environments, though it does not directly enable code execution or data exfiltration.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The natural-language instructions, labels, and examples are all presented exclusively in Chinese, which can amount to a language policy constraint if the skill is used in a broader multilingual environment. The file does not state that the skill is China-specific or otherwise justify the locale limitation, nor does it offer an opt-in language choice.

Static analysis

No suspicious patterns detected.