Fleet Doctrine
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only model-routing skill that tells an agent which model or sub-agent to use for different task types, with no hidden code, installs, credential access, or persistence.
This skill appears low-risk and coherent. Before installing, confirm you are comfortable with your agent using these routing rules to choose models or spawn sub-agents, since that may affect cost, latency, and which providers handle a task.
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
57/57 vendors flagged this skill as clean.