Security audit
TinkerClaw Command Center
Security checks across malware telemetry and agentic risk
Overview
The skill file scans clean, but it directs users to build an unpinned third-party OpenClaw fork that appears broader than the advertised read-only dashboard.
Review the tinkerclaw fork before building it, pin a specific commit if you proceed, and assume the dashboard can display raw prompts, tool outputs, usage data, and local gateway session details. Prefer a narrowly packaged Tinker plugin/UI over replacing your OpenClaw runtime with the whole fork.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.