ClawHub
Back to skill

Security audit

Bank Compliance Review

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only bank compliance review skill that gives draft checklists and recommendations, with clear limits requiring human review before any official action.

Use this as an internal drafting and checklist aid only. Do not paste unmasked customer identifiers or full transaction records, and have qualified compliance staff verify any AML, KYC, reporting, customer restriction, or marketing-material decision before acting on it.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad phrases such as “合规审查”, “合规审核”, “监管合规”, and “合规风险”, which can activate the skill during ordinary compliance discussions that are not specific to bank compliance review. In an enterprise assistant environment, overbroad invocation can route unrelated user content into a domain-specific workflow, increasing the chance of inappropriate guidance, privacy over-collection, or bypass of more suitable guardrails and skills.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 155)May include surrounding context.

md
|------------|----------|------------|---------|------------|---|
| Missing Risk Disclosures | 未披露产品风险、净值波动 | MEDIUM | 首屏海报、朋友圈九宫格 | 只展示业绩比较基准不展示回撤 | 风险揭示与业绩展示同屏、同级呈现 |
| Incomplete Fee Disclosures | 手续费、管理费披露不完整 | MEDIUM | 产品说明书尾部小字 | 只写"费率详见合同" | 在首屏列明各类费率及计费方式 |
| Regulatory Sensitive Terms | CBIRC/CBDRC regulated terms without approval | MEDIUM | 对外新闻稿、公众号 | 未经核准使用"存款""保险"界定词 | 取得核准后再使用相关界定词 |
| Competitive Disparagement | 贬低其他银行/金融机构产品 | MEDIUM | 客户经理对比话术 | "他家收益低、不灵活" | 改为客观参数比较，不评价同业产品 |
| Missing Legal Disclaimer | 缺少法定免责声明 | HIGH | 短视频结尾、H5 页面 | 无"理财有风险，投资需谨慎" | 在显著位置补充标准免责声明 |

Static analysis

No suspicious patterns detected.