ClawHub
Back to skill

Security audit

Aftership for Shopify via Agiexa

Security checks for vulnerabilities and agentic risk

Overview

This prelaunch preview offers optional waitlist signup with explicit consent, though its capability and privacy descriptions need clearer wording.

Install for a preview, not live shipment or return management. Joining the waitlist shares your email, role, and any optional URL or message with Agiexa. The optional URL can identify your store despite the broad privacy assurance. Publisher security claims were not independently verified.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The metadata presents operational AfterShip capabilities, while the actual task-handling instructions defer those capabilities until launch and offer waitlist registration. This is a capability-disclosure mismatch that could steer users seeking shipment assistance into providing marketing contact information, but explicit consent and conversation-confirmed details substantially limit the risk; the registration is not covert or unauthorized as written.

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/aftership
---

The manifest advertises operational AfterShip tools, but the skill defers those tasks and implements waitlist registration instead.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

This is the same capability-disclosure issue as TP4, rather than a separate escalation path: the advertised operational skill instead explains a future launch and offers registration. The required launch disclosure, one-time offer, and explicit permission prevent the stronger conclusion that the skill silently substitutes a data-collection workflow.

Content

No source excerpt is available for this finding.

The privacy statement denies sending store information despite explicitly submitting an optional Shopify store URL.

Low
Category
Excessive Agency
Confidence
96% confidence
Finding

The blanket assertion that nothing about the user's store is sent conflicts with the optional Shopify store URL explicitly included in the registration payload. Although the user supplies and confirms that field, the inaccurate privacy assurance can undermine informed consent about disclosing a store identifier to Agiexa.

Content

No source excerpt is available for this finding.