ClawHub
Back to skill

Security audit

AML/KYC Documentation Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only UK AML/KYC document-template generator with clear limits, but users should avoid entering unnecessary sensitive personal or SAR details.

Before installing, treat outputs as templates only. Do not paste full identity documents, account numbers, unnecessary personal data, or confidential SAR details unless your organisation has approved the platform for that use; use placeholders or redacted details where possible and have a qualified compliance or legal professional review final documents.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is user-invocable and advertises a broad compliance/documentation capability, which can cause it to activate for generic AML, KYC, onboarding, or compliance requests that may exceed the intended narrow scope of template generation. In this context, over-broad routing is risky because the skill contains detailed regulatory and SAR-drafting instructions, so accidental invocation could lead users to rely on templated compliance outputs in situations requiring legal judgement or verified screening.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The listing explicitly offers generation of AML/KYC records, source-of-funds declarations, beneficial ownership verification records, and SAR drafts, all of which commonly involve highly sensitive personal, financial, and potentially criminal-suspicion data. While the skill notes it does not perform verification, it does not warn users about data minimization, secure handling, storage, redaction, or the legal sensitivity of submitting customer and SAR-related information into an AI system, which creates meaningful privacy, confidentiality, and regulatory risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction "Use UK English throughout" forces a specific locale for all outputs and does not offer the user a choice. This is a natural-language policy concern because it imposes a language/locale preference without opt-in or a documented exception mechanism.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.