ClawHub
Back to skill

Security audit

customer-onboarding-guider

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Chinese skill for treasury-system customer onboarding, with no code execution or persistence, though users should treat its live-transaction verification guidance carefully.

Install only for Chinese-language treasury or bank-enterprise integration support. Before following the production verification steps, confirm approvals, amount limits, designated accounts, rollback contacts, monitoring, and reconciliation with the bank and internal finance controls.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are broad enough that ordinary customer questions like '如何对接' or '流程是什么' could activate the skill outside a tightly scoped treasury-integration context. This can cause unintended routing, leading the agent to provide onboarding workflow guidance when the user meant a different process, reducing reliability and potentially exposing internal procedural details more widely than intended.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Responsibility-related examples like '我们需要做什么' and '银行负责什么' are highly generic and lack domain boundaries, so the skill may activate during unrelated conversations about roles or ownership. In a multi-skill agent, this creates misrouting risk and may cause the assistant to answer with treasury onboarding responsibilities even when the user's question concerns another product or workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document instructs customers to perform production verification with 'small real transactions' but does not require prior authorization, transaction limits, approval workflows, rollback procedures, or explicit warnings about financial and compliance impact. In a treasury/banking onboarding context, this omission can lead users to execute live financial transactions unsafely, causing unintended fund movement, accounting issues, or policy violations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file is entirely presented in Chinese and does not indicate that the skill is region-specific or provide any user opt-in for language/locale. Under the policy rule for natural-language violations, forcing a specific language without user choice can be a locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and the entire FAQ are presented only in Chinese, with no indication that users may choose another language or that the content is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy, a fixed language without user opt-in or explicit justification is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.