Back to skill

Security audit

Instagram for Shopify via Agiexa

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed preview of future Instagram features and an optional waitlist signup that requires your permission.

This version does not operate Instagram. If you join the optional waitlist, Agiexa receives your email, role, and any optional link or message you provide, including a store URL if supplied. No passwords or tokens are needed.

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
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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code only POSTs to Agiexa's agent waitlist endpoint. It does not connect Instagram to Shopify or provide any of the described publishing, messaging, comment-management, or insights functionality. Although the destination is the declared provider, waitlist enrollment is a materially different primary purpose, not merely an implementation detail of those tools.

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/instagram
---

The manifest advertises Instagram action tools, but the skill defers those tasks to a future launch and implements waitlist enrollment instead.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest at L003 describes a skill providing 30 tools for publishing posts, handling comments and messages, and checking insights. However, L071 instructs the agent to defer requests for those capabilities until November 2026, while L083–L103 provide an executable workflow for submitting user contact details to a waitlist endpoint. This materially differs from the operational Instagram integration advertised in the manifest, although the waitlist submission explicitly requires consent.

Content

No source excerpt is available for this finding.