Back to skill

Security audit

Xiao Chuang You Health

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only wellness guidance skill with no code execution or data access, but users should treat its health advice as general wellness information rather than medical guidance.

Install only if you want general Chinese-language wellness suggestions. Verify any symptom-related, acupoint, diet-therapy, or body-constitution advice with a qualified clinician when health conditions, pregnancy, medications, injuries, severe symptoms, or persistent symptoms are involved.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill metadata and description define a very broad health/wellness domain, increasing the chance the skill activates for ordinary conversation that only loosely relates to health. Over-broad routing is dangerous because it can inject health guidance into contexts where the user did not explicitly request it, which is especially sensitive for body, diet, sleep, and symptom-related topics.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger lists include vague, high-frequency terms like “吃什么”, “累”, “调理”, and “按摩”, which can appear in many non-health contexts. This makes accidental invocation likely, causing the agent to provide wellness or body-focused advice when the user's intent is ambiguous, potentially normalizing unverified guidance for sensitive conditions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill provides extensive diet, sleep, bodywork, acupoint, and recovery guidance, including condition-linked recommendations such as insomnia, stomach pain, constitution matching, and post-staying-up recovery, but does not clearly and prominently warn throughout that this is non-medical general information that may be unsafe for individual conditions. In a health context, users may rely on these recommendations instead of seeking appropriate care, especially where contraindications, pregnancy, chronic illness, injury, or medication interactions exist.

Content

No source excerpt is available for this finding.