ClawHub
Back to skill

Security audit

Zendesk for Shopify via Agiexa

Security checks for vulnerabilities and agentic risk

Overview

This skill explains a planned integration and offers a clearly disclosed waitlist signup that requires your permission.

Joining the waitlist shares your confirmed email, role, and optional link or message with Agiexa. Before connecting business accounts later, review individual tool permissions and approval settings. The package documents service security claims but does not independently establish them.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The endpoint and waitlist action match the declared service and purpose. However, the description explicitly conditions registration on user permission, while the supplied code submits unconditionally and asserts consent. The example contact information does not demonstrate disclosure of real user data, but the missing consent gate is a material behavioral mismatch.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 9)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
    homepage: https://agiexa.com/integrations/zendesk
---

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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.

Content

Scanner excerpt · references/tools.md (reported line 30)May include surrounding context.

md
| `ZENDESK_CREATE_CUSTOM_OBJECT_RECORD` | Create a new record for a custom object in Zendesk |
| `ZENDESK_CREATE_CUSTOM_OBJECT_RECORD_ATTACHMENT` | Create an attachment for a custom object record in Zendesk |
| `ZENDESK_CREATE_CUSTOM_STATUSES` | Create a new custom ticket status in Zendesk |
| `ZENDESK_CREATE_DELETION_SCHEDULE` | Create a new deletion schedule in Zendesk that automatically deletes records matching specified conditions on a schedule |
| `ZENDESK_CREATE_DYNAMIC_CONTENT_ITEMS` | Create a new dynamic content item with locale variants in Zendesk |
| `ZENDESK_CREATE_DYNAMIC_CONTENT_ITEMS_VARIANTS` | Create a new locale variant for an existing dynamic content item in Zendesk |
| `ZENDESK_CREATE_END_USER_IDENTITY` | Add an identity (email or phone) to an end user's profile in Zendesk |

Autonomous Decision Making

Medium
Category
Excessive Agency
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.

Content

Scanner excerpt · references/use-cases.md (reported line 32)May include surrounding context.

md
- Apps: Zendesk, Shopify, Yotpo Reviews
- Tools: `ZENDESK_SEARCH_ZENDESK`, `ZENDESK_GET_TICKET_COMMENTS`, `ZENDESK_CREATE_SIDE_CONVERSATION`, `ZENDESK_REPLY_ZENDESK_TICKET`

> Analyze Zendesk tickets and Yotpo reviews related to products sold in my Shopify store. Identify recurring complaints about quality, durability, packaging, sizing, or product performance. Match feedback to the correct products when possible, count supporting records, and summarize representative concerns. Recommend which issues deserve investigation first and draft a response for affected customers. Do not treat an individual complaint as proof of a widespread defect, and do not publish replies or change review visibility without approval.

## Handle Subscription Support Requests