ClawHub
Back to skill

Security audit

Bank Credit Investigation

Security checks for vulnerabilities and agentic risk

Overview

This is a conversation-only credit due-diligence guide that discloses its limits and does not include code, tools, persistence, or credential access.

Before installing, treat this as an analytical template only. Do not paste full bank statements, ID numbers, account numbers, customer lists, supplier lists, or other raw confidential data; verify regulatory claims and any credit recommendation with qualified staff and official sources before use.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list uses generic credit and financial-analysis phrases such as '信用分析', '财务报表分析', and '行业风险', which can match routine requests outside a narrowly scoped bank credit due-diligence workflow. Over-broad activation can cause the skill to engage in unintended contexts, increasing the chance of collecting sensitive financial data or producing authoritative-seeming credit guidance when the user only wanted general analysis.

Static analysis

No suspicious patterns detected.