Security audit
fleet-doctrine
Security checks across malware telemetry and agentic risk
Overview
This skill is a plain-text model-routing guide and does not request unusual access, persistence, or data handling.
Installers should understand that this skill can shape which model class an agent chooses for different tasks, including higher-cost or more capable models, but the artifact itself is transparent guidance rather than active code.
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.
Static analysis
No suspicious patterns detected.