ClawHub
Back to skill

Security audit

Banking

Security checks for vulnerabilities and agentic risk

Overview

This banking skill is a disclosed workflow guide with local note-taking and conservative escalation rules, not an automatic banking or fund-transfer tool.

Before installing, be aware that this skill may create local banking workflow notes under ~/banking/. Do not store customer secrets, full account numbers, credentials, or regulated personal data there; use it as an operational checklist and escalation aid, not as legal advice or an automatic banking action tool.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Unauthorized transaction suspected.
- KYC or sanctions bypass requested.
- Irreversible transfer requested without approvals.
- Legal interpretation requested as definitive advice.
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.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs the agent to persist internal notes in ~/banking/memory.md that may include jurisdiction, account scope, policy constraints, known failure points, incident patterns, and accepted communication templates. In a banking context, these notes can easily contain sensitive operational, customer, fraud-response, or security-control information, and the file-based persistence is requested without minimization rules, storage protections, retention limits, or warnings against storing secrets or regulated data.

Static analysis

No suspicious patterns detected.