ClawHub
Back to skill

Security audit

Account Research

Security checks for vulnerabilities and agentic risk

Overview

This sales research skill is coherent and disclosed, but users should be careful because connected enrichment and CRM data can include personal or confidential business information.

Install this only in environments where users are authorized to access the connected CRM and enrichment data. Treat emails, phone numbers, notes, deal history, and activity timelines as sensitive, and ask the agent to retrieve only the fields needed for the specific sales research task.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly encourages access to verified emails, phone numbers, CRM contacts, notes, and relationship history without any notice about sensitivity, consent, authorization boundaries, or data-minimization. In a sales-research context this can lead to unauthorized collection or overexposure of personal and customer data, especially when users may not realize connector-backed outputs include regulated or confidential information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The execution flow operationalizes searches across enrichment and CRM systems for people, contact lists, opportunity history, and activity timelines, but provides no safeguards around least privilege, purpose limitation, or disclosure to the user. Because these steps are framed as routine workflow, the skill may normalize bulk retrieval of sensitive business and personal data beyond what is needed for the immediate task.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.