Openclaw Agent Builder
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for configuring OpenClaw agents; it describes powerful options, but they are visible, purpose-aligned, and not automatically executed.
Install this only if you intend to build or configure OpenClaw agents. Review any generated hooks, exec permissions, heartbeat tasks, identity links, channel bindings, and memory/session retention before enabling them, and avoid storing raw secrets directly in Markdown workspace files.
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
62/62 vendors flagged this skill as clean.