ClawHub
Back to skill

Security audit

闲鱼爆款标题生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language prompt guide for generating Xianyu listing titles, descriptions, and customer-service scripts, with no code execution or sensitive access.

Install this if you want Chinese Xianyu sales-copy templates. Review generated claims such as refunds, delivery times, and guarantees before posting so they match what you actually offer.

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
96% confidence
Finding

The activation description contains many broad trigger phrases such as '闲鱼怎么写', '闲鱼文案', and other generic wording that can match ordinary user conversation far beyond the intended scope. This can cause over-activation of the skill, leading the agent to inject specialized marketplace-selling behavior into unrelated requests and reducing user control over which tool is invoked.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

All user-facing instructions and examples are written exclusively in Chinese, and the skill implicitly assumes Chinese-language outputs for titles and scripts. There is no statement that the language is optional, user-selected, or required for a documented region-specific purpose.

Content

No source excerpt is available for this finding.