Deepagents Architecture
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only architecture guide and does not install code, request credentials, or perform actions by itself.
Safe to install as a reference skill. If you use its advice to build a Deep Agents application, explicitly scope filesystem roots, command execution approvals, subagent tool access, and memory retention before implementation.
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
66/66 vendors flagged this skill as clean.