ClawHub
Back to skill

Security audit

AI编程与低代码产品项目搭建

Security checks for vulnerabilities and agentic risk

Overview

This is a simple AI-assisted coding guidance skill with broad activation wording but no hidden code, persistence, credential handling, or destructive behavior.

Installers should expect this skill to activate for general programming and low-code project-building prompts. Review generated code before running it, especially when it installs packages, calls external APIs, handles files, or uses credentials.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises trigger phrases that are broad enough to match ordinary requests for general coding help, which can cause this skill to activate outside its intended scope. Over-broad activation increases the chance of unintended routing, prompt hijacking of normal conversations, and inappropriate exposure of a powerful code-generation workflow in contexts where the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example trigger list includes the generic pattern '帮我写个XXX脚本/工具/网站', which overlaps heavily with common user requests and could capture a large volume of unrelated prompts. In an agent ecosystem, this creates unsafe ambiguity in skill selection and may let this skill intercept requests that should remain with the base assistant or a more specialized, safer skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.