ClawHub
Back to skill

Security audit

Medical Entity Extractor

Security checks for vulnerabilities and agentic risk

Overview

The skill is simple and purpose-aligned, but it should be reviewed because it handles patient data and understates that a recommended Claude API model may receive that data.

Install only if you are comfortable with the configured OpenClaw model receiving patient-message content. For PHI-sensitive workflows, use a locally hosted model or confirm appropriate consent, data-processing terms, retention controls, and healthcare compliance requirements before use.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The privacy section claims that all processing happens locally while also disclosing an exception for Claude API processing, which means patient messages and extracted medical details may be transmitted to an external third-party service. In a medical context, this understatement is dangerous because users may assume PHI stays local and may unknowingly send sensitive health data to an external processor, creating privacy, compliance, and consent risks.

Content

No source excerpt is available for this finding.