ClawHub
Back to skill

Security audit

Client Onboarding Automation

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent client-onboarding automation guide, but it asks agents to collect and store highly sensitive client documents and payment information without adequate scoping or security guidance.

Review this skill carefully before installing. Use it only with scoped client data, secure upload and storage systems, explicit consent, retention/deletion rules, role-based access, and PCI-compliant payment handling; do not put IDs or payment information into ordinary spreadsheets or email workflows without appropriate safeguards.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The configuration explicitly requests highly sensitive documents such as ID, contract, and payment information without any safeguards or warnings about secure upload, encryption, masking, or PCI/privacy obligations. If implemented as written, users may collect and store identity and financial data in inappropriate systems like email workflows or Google Sheets, creating substantial risk of data exposure, fraud, or regulatory violations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill automates intake, document collection, CRM storage, and follow-up for client onboarding, which inherently involves handling personal and potentially sensitive business data. The dangerous part is not the automation itself, but the absence of any guidance on consent, data minimization, retention, access controls, or secure storage, which increases the likelihood of insecure or non-compliant deployments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description claims the skill 'works with any service business,' which is an overly broad applicability statement that can cause the agent to surface or invoke this skill in many generic business contexts beyond its validated scope. Overbroad routing increases the chance of inappropriate activation, misuse in unsuitable workflows, or unnecessary exposure of automation capabilities tied to client data, email, and CRM actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.