Agent Builder
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for designing OpenClaw agent workspaces, with its behavior and persistence effects disclosed.
Before installing, confirm the publisher and homepage if provenance matters to you. When using the skill, review any generated AGENTS.md, MEMORY.md, and HEARTBEAT.md files, keep secrets out of memory files, and only enable heartbeat or autopilot behavior when you explicitly want it.
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
64/64 vendors flagged this skill as clean.
