ClawHub
Back to skill

Security audit

Mvp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple MVP-planning guide and does not ask for privileged access, persistence, code execution, or data collection.

Install this if you want Chinese-language guidance for scoping and launching an MVP quickly. Be aware it may be invoked for broad first-product or quick-launch questions, but the artifact does not contain commands or hidden automation.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords and read_when conditions include broad, everyday product-building phrases such as '先做什么' and '怎么快速上线', which can cause the skill to activate outside narrowly intended MVP-planning contexts. This is not directly exploitable for code execution or data theft, but it can lead to unintended invocation, irrelevant guidance, and increased attack surface if the agent routes sensitive or unrelated requests into this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.