ClawHub
Back to skill

Security audit

Neuropsych Evaluation Report

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed clinical draft-writing skill with no code execution, persistence, or hidden data access, but users should treat its output as clinician-reviewed draft material only.

Install only for draft clinical documentation workflows used by qualified neuropsychology professionals. Do not enter full names, DOBs, MRNs, or other identifying patient data unless your institution has approved the AI environment for HIPAA-covered use, and have a licensed neuropsychologist verify language factors, test validity, diagnostic language, codes, and recommendations before any release.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
85% confidence
Finding
The skill constrains primary language collection to 'English / Other,' which can bias workflow toward English and fails to explicitly support multilingual assessment or user-selected language preferences. In a neuropsychological evaluation context, language proficiency and interpreter use materially affect test validity, so oversimplified language handling can lead to inaccurate documentation, inappropriate test interpretation, or inequitable care.

Static analysis

No suspicious patterns detected.