Back to skill

Security audit

Gout Diagnosis

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language gout assessment guide with medical-safety caveats, not a skill that installs code, persists, or accesses data outside the user’s provided medical details.

Install only if you want a Chinese-language gout likelihood checklist. Do not rely on it as a diagnosis, especially with fever, severe trauma, rapidly worsening symptoms, suspected infection, or abnormal imaging; a clinician should make the final diagnosis.

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 (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes the single broad term '痛风' ('gout'), which can activate the skill in many contexts beyond an explicit request for diagnostic assistance. In a clinical-assessment skill, overbroad invocation can cause unsolicited medical scoring or quasi-diagnostic output when the user may only be mentioning the condition, increasing safety and misdiagnosis risk.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description and operational content are entirely in Chinese, with no indication that the user may choose another language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when a skill implicitly forces one language without opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation conditions are loosely defined, such as triggering whenever the user provides history and asks whether gout can be diagnosed, without clear safeguards for uncertainty, emergency symptoms, or user consent to proceed through a structured assessment. This ambiguity increases the chance of the skill being applied outside appropriate scope, producing overconfident clinical guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.