Security audit
OpenClaw Safe Config
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed safety checklist for editing OpenClaw configuration, with backups and validation before restart.
Install only if you are comfortable letting an agent help edit ~/.openclaw/openclaw.json and restart the OpenClaw gateway. Review any proposed changes to session visibility, agent-to-agent messaging, and tool allow/deny settings before writing them.
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.