ClawHub
Back to skill

Security audit

创业启动助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a China-focused startup administration guide with a simple checklist generator and no evidence of hidden access, data exfiltration, persistence, or destructive behavior.

Install this only if you want Chinese-language guidance for China-based startup administration. Treat legal, tax, ICP, trademark, and fee information as checklist-style guidance and verify current requirements with official agencies or qualified local professionals before acting.

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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger description is very broad and matches many ordinary entrepreneurship-related queries, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of inappropriate routing, misleading procedural/legal guidance in the wrong context, and accidental collection of business-sensitive information when a more specialized or locale-aware tool should respond.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written and positioned entirely in Chinese for China-specific administrative processes, but it does not clearly declare a locale/language restriction or offer a language fallback. This can mislead non-Chinese-speaking users or users in other jurisdictions into relying on inapplicable compliance guidance, increasing the risk of procedural mistakes and misunderstanding of legal requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The package description is entirely in Chinese and presents the skill as a general-purpose startup helper, but it does not indicate that the tool is region-specific or that users may opt into another language. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The workflow guidance, headings, and Q&A content are all presented exclusively in Chinese, which effectively forces a specific language for users. The file does not indicate that the skill is intended only for Chinese-speaking or China-specific users, nor does it offer an opt-in or alternative language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file presents its purpose and usage in Chinese and later formats dates with zh-CN while all console output and generated markdown content are Chinese-only. This enforces a specific language/locale without user opt-in, which matches the policy-violation criterion for language or locale restrictions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill file is written only in Chinese and presents the checklist as a general-purpose startup guide, with no indication that the language is optional or limited to users who requested Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language locale violation unless the regional constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.