OpenClaw Shield
Security checks across malware telemetry and agentic risk
Overview
This appears to be a real security-scanner skill, but it asks users to fetch and run unpinned external code that was not included in the reviewed package.
Review the external GitHub repository before running it, pin a specific commit, restrict scan targets to intended directories, and enable cron or Telegram alerts only after confirming exactly what data is logged or transmitted.
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.