ClawHub
Back to skill

Security audit

SellerSprite MCP

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent SellerSprite/OOMOL connector wrapper, but its setup instructions include unverified remote script execution for installing the required CLI.

Install only if you trust OOMOL and SellerSprite for this account workflow. Before running the CLI installer, prefer an official package-managed or checksum-verified installation path, and review any write-capable SellerSprite MCP payload before approving it.

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 users to install software via curl ... | bash, which executes a remote script directly without prior verification, pinning, or integrity checking. If the remote host, transport path, or published script is compromised, this becomes an immediate arbitrary code execution path on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says to use this skill for ANY SellerSprite MCP request and instead of calling the API directly, which is broad enough to trigger the skill in situations where a narrower, more task-scoped skill or direct review would be safer. Over-broad routing increases the chance of unintended invocation, especially because this skill includes both read actions and a write-capable call_tool action.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.