ClawHub
Back to skill

Security audit

Clinico Geral

Security checks for vulnerabilities and agentic risk

Overview

This is a Portuguese medical-information skill with visible safety disclaimers and no code, tools, credential access, persistence, or hidden data handling.

Before installing, users should understand this skill is for educational medical information in Brazilian Portuguese and should not be relied on for diagnosis, treatment decisions, medication dosing, or urgent care; emergencies should go to local emergency services or a health professional.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

A descrição de ativação é muito ampla e cobre praticamente qualquer dúvida médica, sintoma, medicamento, exame ou emergência. Em um domínio de alto risco como saúde, isso aumenta a chance de a skill ser acionada em situações complexas, urgentes ou inadequadas para orientação automatizada, podendo induzir confiança excessiva ou respostas fora do escopo seguro.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

A instrução 'Responder sempre em português do Brasil' força um idioma/localidade específico independentemente da preferência do usuário. Pelas regras, isso configura violação de política de idioma/locale quando não há opt-in nem justificativa regional explícita.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.