Security audit
claw-helper
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only OpenClaw help skill whose disclosed CLI and note-writing behavior fits its troubleshooting purpose.
Safe to install for OpenClaw help. Before allowing it to run `openclaw config set` or update local notes/index files, review the exact change, and do not let it save tokens, passwords, private logs, or unverified fixes into the experience notes.
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.