ClawHub
Back to skill

Security audit

商业点子体检官 Idea Doctor

Security checks for vulnerabilities and agentic risk

Overview

This skill openly offers a paid, online business-idea assessment, with ordinary privacy and payment-installation risks.

Submit only information you are comfortable sharing with linkkhub.top, and ask about retention before sending confidential plans. Review the payment prerequisite, preferably using a reviewed package version, and personally verify the merchant and amount before authorizing payment. Scanner coverage was complete for the sole bundled file; server behavior and downloaded payment code remain unverified.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends business ideas and financial assumptions to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow requires transmitting business ideas, scoring inputs, and financial assumptions to an external service without explaining confidentiality, retention, or downstream use. Remote processing is openly described and integral to the service, so this is not evidence of covert exfiltration; nevertheless, users could disclose proprietary plans without understanding the privacy implications. The business-evaluation context makes these inputs potentially commercially sensitive.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y @alipay/agent-payment'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The documented command uses npx -y @alipay/agent-payment@latest install, automatically fetching and executing a mutable package version without a package-install confirmation. A compromised release could execute code with the host user's privileges; the payment authorization context increases the potential consequences, although no malicious package behavior is demonstrated. The finding incorrectly calls this an MCP server, but the underlying unpinned CLI execution risk is valid.

Content

No source excerpt is available for this finding.