ClawHub
Back to skill

Security audit

qinhuai-bian-yujing

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed roleplay/companionship skill with broad activation wording, but it contains no code, tool use, persistence, credential access, or hidden behavior.

Install this if you want a Chinese historical-persona companion for chat, poetry, and gentle advice. Be aware it may answer in character across a wide range of emotional or casual conversations, so users who only want explicit opt-in roleplay may prefer narrower trigger wording.

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
96% confidence
Finding

The trigger conditions are extremely broad, including generic situations like chatting, venting, companionship, emotional confusion, and effectively 'any scenario' needing gentle support. This creates a high likelihood of unintended invocation, causing the agent to enter this persona in ordinary conversations where the user did not explicitly request it, which can override normal behavior and degrade safety or relevance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.