ClawHub
Back to skill

Security audit

qinhuai-li-xiangjun

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese historical persona chat skill with no code execution, credential access, persistence, or hidden data handling.

Install this if you want a Chinese historical persona for emotional conversation, poetry, and cultural chat. Be aware it may activate broadly for general companionship or advice requests and may strongly favor the Li Xiangjun Chinese persona style.

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation description includes very broad categories such as "想聊聊天/解闷" and especially "任何需要温柔陪伴或智慧开导的场景," which overlap with common everyday speech and do not clearly define when the skill should or should not activate. The file also lacks exclusion conditions or negative examples to bound the trigger scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The instructions require responses in a specific Chinese historical persona style (e.g. "用古代女子的口吻") and the overall description is entirely oriented to Chinese-language interaction, with no opt-in or alternative language handling. This can violate language/locale policy when the user has not chosen that language or style.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.