ClawHub
Back to skill

Security audit

PsyVector pv52

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese crisis-consultant roleplay skill with no executable code, persistence, or hidden data movement.

Install this if you want a Chinese-language crisis-advisory persona. Be aware it may activate on common crisis or risk words and may use web research or available internal-data tools during crisis analysis, so use it in contexts where that behavior is acceptable.

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 trigger phrases are broad, common terms like '风险', '紧急', '出问题', and '失控' that can appear in many normal conversations, causing the skill to activate outside its intended scope. Unintended activation can override user expectations, force roleplay behavior, and change response style or workflow in unrelated contexts, especially because the skill instructs the agent to directly assume the role once triggered.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill metadata and content are entirely Chinese-centric and define fixed trigger phrases and role behavior without offering user choice of language or locale. This can lead to unwanted language switching or exclusion of users who did not request Chinese output, reducing usability and potentially causing misunderstanding in high-stakes crisis discussions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.