ClawHub
Back to skill

Security audit

Psychology Assessment Creator

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language guide for creating psychological assessment content; it does not install code or request system access, but users should add clear non-diagnostic disclaimers.

Before installing, confirm that a Chinese-language psychological-assessment writing guide is what you want. For any public-facing assessment, add clear wording that results are for self-reflection only, are not diagnosis or treatment, and are not a substitute for licensed professional help; include escalation guidance for high-risk mental-health topics.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill provides end-to-end guidance for creating psychological assessments and result narratives, but it does not prominently require a user-facing disclaimer that outputs are for self-reflection only and are not diagnosis, treatment, or professional mental-health advice. In this context, users may over-trust personalized results, especially when the skill encourages high-credibility framing, which can mislead vulnerable users or delay appropriate care.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest description is entirely in Chinese and the document provides no indication that language choice is optional or that the skill is intentionally restricted to a Chinese-speaking region or audience. Under the language/locale policy, forcing a specific language without user opt-in or justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.