ClawHub
Back to skill

Security audit

dealcenter

Security checks for vulnerabilities and agentic risk

Overview

This skill uses a DealCenter customer-records connector for customer context and user-approved CRM updates, with clear limits around when writes may happen.

Install this only if you intend the agent to access DealCenter customer records and, when you explicitly approve, create or update customer, contact, deal, activity, or document records. Review confirmations carefully because approved writes can persist in business records.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file documents multiple persistent write-capable CRM tools (account.create, contact.upsert, deal.upsert, deal.advance, doc.create, activity.batch_create) and their required payloads, but it does not include a clear user-facing safety warning or enforcement note that writes must only occur with explicit user authorization. In a customer-records skill, silent or ambiguous use of these tools can cause unauthorized modification of business data, audit contamination, and privacy/compliance issues because the agent is given enough detail to perform durable writes once invoked.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.