Back to skill

Security audit

Haodf

Security checks for vulnerabilities and agentic risk

Overview

This is a simple doctor-finding instruction file with no executable code, but users should treat its medical routing and emergency-number guidance as locale-limited and verify it independently.

Install only if you want a lightweight doctor-search and specialty-routing prompt. Do not rely on it for diagnosis, treatment, medication decisions, or emergency instructions; use your local emergency number and verify doctor availability, ratings, and booking details with the hospital or provider directly.

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
  • 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

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger scope is broad enough to activate on general medical-information queries, not just doctor-finding tasks. In a healthcare context, this can cause the skill to engage when users are seeking symptom interpretation or treatment guidance, increasing the chance of overreach, incorrect routing, or unsafe pseudo-medical recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-codes the emergency number '120,' which is only appropriate in certain locales. If used for users outside China, this could delay urgent care by directing them to the wrong emergency service, making the issue more serious because it appears in emergency guidance within a medical skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.