ClawHub
Back to skill

Security audit

qinhuai-gu-hengbo

Security checks for vulnerabilities and agentic risk

Overview

This is a low-impact roleplay companionship skill with broad activation wording but no code execution, data access, persistence, or hidden privileged behavior.

Install this if you want a stylized Gu Hengbo persona for companionship, emotional reflection, poetry, and history. Be aware it may answer broadly in character for casual or advice-oriented conversations, and treat any external contact or marketplace link in the author section as promotional rather than required for the skill to function.

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
97% confidence
Finding

The trigger conditions are extremely broad, including '想聊聊天/解闷' and effectively 'any scenario needing gentle companionship or advice,' which can cause the skill to activate for routine conversation without clear user opt-in. This is not an exploit in the traditional sense, but it creates scope-control risk: the persona may override normal assistant behavior unexpectedly and handle topics beyond its intended domain.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill mandates a specific speaking style and role persistence ('始终以顾横波的身份对话') without user opt-in, which can conflict with user expectations and reduce transparency. In benign companionship content this is lower risk, but it can still mislead users into receiving stylized or historically framed responses when they did not explicitly request that mode.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.