Admet Prediction

• Outcome: Pass
• Latest audit: May 28, 2026 at 12:44 PM UTC
• Version:
  0.1.0

Overview

This skill appears to be a local ADMET research helper, with no evidence of hidden data access, persistence, or exfiltration.

Install dependencies in a virtual environment and only run the tool on compound files you intend to analyze. Treat hERG, DILI, Ames, PK, and progression recommendations as research screening signals only; validate important safety and development decisions experimentally.

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 (1)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill provides toxicity, PK, and 'progress to in vivo PK' style recommendations, but the warning language is limited to general model limitations and does not clearly state that outputs are decision-support only and must not be used as definitive safety, medical, or go/no-go decisions. In a drug-discovery context, users may over-trust these outputs and make unsafe prioritization or de-prioritization decisions based on uncertain predictions.

VirusTotal

66/66 vendors flagged this skill as clean.