Security audit
classical-ml-drug-discovery
Security checks across malware telemetry and agentic risk
Overview
This skill provides a local drug-discovery modeling workflow with clear scientific and privacy limits, and I did not find hidden or unrelated behavior.
Install in an isolated Python environment, review dependency licenses for commercial use, and only use --trust-model with model.joblib files you created or otherwise trust. Do not upload proprietary structures or assay labels to optional third-party websites unless you have authorization.
SkillSpector
By NVIDIA
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
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.