Pathology-PMPH-10edition

• Outcome: Review
• Latest audit: Jun 7, 2026 at 2:33 AM UTC
• Version:
  1.0.0

Overview

This is a medical pathology skill library with no malware signals, but it gives diagnosis and treatment guidance without consistent clinician-oversight and emergency-safety boundaries.

Treat this as Review rather than malware: install only if you want an educational or clinician-reviewed pathology reference. Do not use it as a standalone source for diagnosis, cancer therapy selection, anticoagulation/thrombolysis decisions, or emergency triage; verify outputs with qualified medical professionals and current local guidelines.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Missing User Warnings

High

• Confidence: 97% confidence
• Finding: The skill gives a definitive benign diagnosis and explicitly states no malignant-tumor handling is needed, without requiring qualified clinician/pathologist confirmation, uncertainty handling, or escalation criteria. In a medical diagnostic context, this can create false reassurance and delay cancer workup if the lesion is misclassified or if relevant clinical/pathologic features are incomplete.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: This skill provides structured guidance for diagnosing and classifying coronary heart disease, including acute coronary syndromes, but does not include a clear escalation warning for emergency symptoms such as ongoing chest pain, dyspnea, syncope, or suspected myocardial infarction. In a medical context, omission of urgent-care instructions can delay emergency evaluation and treatment, which is especially dangerous because CHD and ACS are time-sensitive and potentially fatal conditions.

Missing User Warnings

High

• Confidence: 97% confidence
• Finding: The index presents numerous diagnostic, staging, prognosis, and treatment-guiding medical skills as directly usable workflows without any visible limitation statement, clinician-oversight warning, or emergency-care escalation guidance. In a high-risk medical context, users may over-rely on generated outputs for diagnosis or treatment decisions, creating a material patient-safety risk even if the content is educationally intended.

Missing User Warnings

High

• Confidence: 95% confidence
• Finding: The skill gives mutation-specific treatment recommendations for NSCLC, including named targeted drugs, without clearly stating that this is informational support only and must not be used as a standalone basis for treatment. In a medical context, users may over-trust the workflow and apply incomplete or outdated guidance, creating a real risk of inappropriate cancer therapy selection.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly outputs intervention directions such as anticoagulation, thrombolysis, and thrombectomy without requiring clinician oversight or a clear medical disclaimer. In a medical pathology skill, this can be acted on as treatment guidance, creating a real risk of unsafe self-management or inappropriate clinical decision support for conditions where wrong therapy can cause major bleeding, delayed care, or death.

VirusTotal

64/64 vendors flagged this skill as clean.