ClawHub
Back to skill

Security audit

qinhuai-liuru-shi

Security checks for vulnerabilities and agentic risk

Overview

This is a conversational historical persona skill with broad activation wording, but no code, tools, data access, persistence, or hidden privileged behavior.

Install this if you want a Chinese-language Liu Rushi persona for literary, historical, and supportive conversation. Be aware it may activate broadly for casual chat or emotional-support prompts, so users who prefer narrower behavior may want clearer activation wording, but the inspected package does not show security-sensitive access or persistence.

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
95% confidence
Finding

The trigger conditions are extremely broad, including ordinary needs like chatting, companionship, emotional support, literature, and 'any' scenario needing gentle company or guidance. This can cause the persona to activate in many unrelated conversations, increasing the chance of unintended role takeover, user confusion, and interference with other more appropriate skills or system behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.