ClawHub
Back to skill

Security audit

ShipEngine for Shopify via Agiexa

Security checks for vulnerabilities and agentic risk

Overview

The skill explains a planned shipping integration and offers a clearly disclosed waitlist signup that requires explicit permission.

This skill provides information and optional waitlist signup, not working shipping tools. Joining shares your confirmed contact details with Agiexa. Keep optional notes free of secrets; future account connections require a separate review of permissions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The endpoint and registration purpose match the description. However, the description explicitly conditions signup on user permission, while the supplied shell command immediately submits the registration with consent set to true. No permission check or consent-dependent execution is shown. The placeholder values do not demonstrate disclosure of actual user information, but they do not resolve the consent 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/shipengine
---