Security audit
Coder for OpenClaw
Security checks across malware telemetry and agentic risk
Overview
This is a transparent setup guide for a powerful OpenClaw coding sub-agent; its risks are disclosed and aligned with its purpose.
Before installing, review the linked repository, Dockerfile, agent configuration, and runtime prompt; consider pinning a trusted commit. Use an isolated workspace, avoid mounting secrets or sensitive directories, validate OpenClaw sandbox settings, watch provider data exposure, and remove the openclaw.json agent entry when it is no longer needed.
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.
Static analysis
No suspicious patterns detected.