Agent Subagents UI
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only OpenClaw UI development skill whose persistent config changes are disclosed and aligned with its purpose.
Install this if you want an agent to modify the OpenClaw Agents-page Subagents UI. Review generated diffs carefully, especially shared subagent defaults and limits, and run the suggested pnpm checks only in a trusted OpenClaw repository.
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.