OpenClaw Security Hardening Toolkit
Security checks across malware telemetry and agentic risk
Overview
The available artifacts are coherent developer workflow skills with disclosed command use and user-directed guardrails, though some workflows can perform high-impact maintainer actions.
Install only if you want ClawHub/Convex maintainer and developer workflow assistance. Review proposed commands before allowing writes, especially moderation actions, GitHub publishing, Convex deployment commands, package installs, and the autoreview helper's default full-access nested Codex review mode.
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
66/66 vendors flagged this skill as clean.