ClawHub
Back to skill

Security audit

Bank

Security checks for vulnerabilities and agentic risk

Overview

This is a static banking advice skill with no executable behavior, persistence, credential access, or hidden data movement, though users should verify jurisdiction-specific dispute and regulatory guidance.

Before installing, understand that this skill gives banking guidance, not account access or automated actions. Verify interest rates, bank terms, fee policies, and dispute deadlines with your bank or local regulator, especially outside the United States or when legal rights are involved.

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

High
Confidence
97% confidence
Finding
The trigger description is extremely broad and includes catch-all language like 'any scenario involving the relationship between a person and the institutions that hold their money,' which can cause the skill to activate for loosely related finance conversations. In an agent setting, overbroad invocation is a real security and safety issue because it increases the chance the model applies banking-specific guidance in contexts where it lacks the right scope, jurisdiction, or expertise.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill provides procedural dispute and regulatory-escalation guidance as if generally applicable, but does not consistently warn that timelines, legal protections, and complaint channels are jurisdiction-specific and not legal advice. That can mislead users into relying on inaccurate rights, deadlines, or agencies, especially outside the US, causing financial harm or missed dispute windows.

Static analysis

No suspicious patterns detected.