ClawHub
Back to skill

Security audit

Medical Document Processor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple medical-document summarization prompt with privacy cautions and no code, network access, persistence, or hidden behavior.

Install only if you want an assistant to process medical documents you provide. Avoid pasting patient identifiers unless needed, and explicitly ask for the language and format you want because the skill defaults to Chinese structured Markdown.

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

Medium
Confidence
93% confidence
Finding
The trigger list includes broad terms like '病歷', '醫療報告', '醫學文獻', 'clinical notes', and 'medical document' that are likely to match ordinary user conversation rather than a clear intent to invoke this specific skill. In a medical context, accidental activation is more concerning because users may paste sensitive health information, causing the skill to process protected data unexpectedly or in the wrong workflow.

Natural-Language Policy Violations

Low
Confidence
72% confidence
Finding
The file specifies a default structured Markdown output and the surrounding documentation is entirely Chinese, but it does not explicitly offer users a choice of output language despite including both Chinese and English trigger terms. This can create a language/locale policy issue because the skill appears to assume a specific language presentation without opt-in.

Static analysis

No suspicious patterns detected.