ClawHub
Back to skill

Security audit

AI商家搜索优化

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language local business marketing guide that generates AI-search-friendly media content and does not install code, request tools, or add persistence.

Install only if you want Chinese-language guidance for local business AI-search marketing. Before generating or publishing articles, confirm the merchant has authorized use of the exact business name, address, and phone number and that the claims in the content are accurate.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly requires collection of a merchant’s full address and phone number and instructs that these details be republished in generated media articles. Even if this is business information rather than personal consumer data, the workflow lacks any user-facing consent, minimization, or privacy notice, which increases the risk of unnecessary disclosure, doxxing of sole proprietors, and publication of sensitive contact/location data at scale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README’s user-facing instructions and description are entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking region. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire skill description and workflow are presented only in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language audience for compliance or regional reasons. This creates a natural-language locale constraint without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.