ClawHub
Back to skill

Security audit

Coupang

Security checks for vulnerabilities and agentic risk

Overview

The Coupang connector is mostly coherent, but it needs review because setup tells the agent to run an unverified online installer while the skill can affect seller account data.

Review the OOMOL oo CLI installer before allowing setup, prefer a verified or pinned installation path, and do not let an agent run first-time setup unattended. For use after setup, confirm exact item IDs, prices, quantities, and effects before approving destructive Coupang actions.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs fetching and piping a remote installer directly into a shell (curl ... | bash), which executes unverified code from the network immediately. If the distribution endpoint, transport path, or hosted script is compromised, this can lead to arbitrary code execution on the user's machine under the current user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description explicitly says to use this skill for ANY Coupang request, including read, create, update, and delete operations, without narrowing scope or requiring additional routing checks. That broad trigger can cause the agent to invoke a powerful integration in situations where a more constrained path would be safer, increasing the chance of unintended data access or state-changing operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.