认知理解与策略建模
Security checks across malware telemetry and agentic risk
Overview
This is a text-only task analysis skill that helps structure reasoning and does not request code execution, system access, credentials, persistence, or external data access.
This appears safe to install for structured task analysis. It may influence how an agent frames complex work and recommends follow-up roles or decomposition, but the artifact does not itself execute actions or access external resources.
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
65/65 vendors flagged this skill as clean.