ClawHub
Back to skill

Security audit

Wx Title Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides headline optimization for WeChat-style articles; its triggers are somewhat broad but it does not request tools, credentials, persistence, or external access.

Install this if you want a structured WeChat public-account headline helper. Be aware that generic requests about headlines or title rewriting may activate this skill even when you meant a different publishing context.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill's trigger phrases include generic terms like '优化标题', '标题改写', and 'headline', which can match many ordinary user requests outside the intended WeChat public-account context. This can cause unintended skill activation, leading to scope confusion, inappropriate formatting constraints, or the model applying this skill when a more relevant one should handle the request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.