02 Risk Scoring
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only risk-scoring skill for logistics suppliers and pickup stations, with no code execution or hidden access, but users should treat its business recommendations as advisory and protect sensitive records.
Before installing or using this skill with real supplier or station records, verify that the scoring rules are authorized for your organization, redact unnecessary personal identifiers such as names, phone numbers, addresses, and complaint narratives, and require a qualified human reviewer before taking suspension, termination, or clearance actions.
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
63/63 vendors flagged this skill as clean.