ClawHub
Back to skill

Security audit

Build Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a planning-only skill for building web or WeChat Mini Program MVPs, with no executable code, persistence, credential access, or hidden data handling.

Before installing, note that this skill may steer planning toward common default stacks such as Next.js, Supabase, Stripe, Taro, and WeChat Cloud. Confirm your target platform, region, and preferred technologies so its roadmap stays aligned with your project.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation description includes broad trigger phrases such as 'roadmap', '怎么开发', and 'development plan', which can match many generic user requests and cause the wrong skill to activate. Over-broad routing is dangerous because it can override more appropriate skills, produce irrelevant guidance, and expand the attack surface for prompt-routing manipulation if an adversary intentionally uses common trigger terms.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The instruction positions the skill as planning for 'indie web products and WeChat Mini Programs', which introduces a specific regional/platform context in the natural-language behavior. Because the file does not explicitly ask the user whether they want a WeChat Mini Program path versus another locale/platform-specific option, it can steer users into a locale-specific workflow without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

Line L32 embeds a specific Chinese-language locale requirement ("微信小程序平台运营规范") as an instruction without any user opt-in or alternative locale guidance. This can be a natural-language policy issue because the file effectively forces a specific language/locale in the workflow rather than offering a choice or documenting why the locale constraint applies.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.