ClawHub
Back to skill

Security audit

qinhuai-kou-baimen

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed roleplay companionship skill with no executable code, tool use, persistence, or credential/data access.

Install this only if you want a broad historical-persona companion that may answer many emotional, literary, or casual chat prompts in character. Do not treat it as professional mental-health, medical, legal, or safety-critical advice.

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
97% confidence
Finding

The trigger condition includes broad phrases such as '想聊聊天/解闷' and '任何需要温柔陪伴或智慧开导的场景', which can cause the persona to activate for an extremely wide range of unrelated user inputs. Overly broad activation increases the chance of unintended role takeover, response misalignment, and inappropriate handling of sensitive situations that should instead receive neutral, domain-specific, or safety-escalated responses.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.