Auto Proteomics
Security checks across malware telemetry and agentic risk
Overview
This skill is a local proteomics workflow with clear scope and no evidence of hidden access, exfiltration, or persistence.
Install this only if you need the narrow processed DDA LFQ workflow. Treat DIA, raw-search, phospho, enrichment, and multi-omics files as prototype or scaffold material, and do not run the release staging script with a custom output directory unless you have verified it points to a disposable folder.
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.