Security audit
Geekbench
Security checks across malware telemetry and agentic risk
Overview
This Geekbench skill is mainly for public benchmark lookups, with optional helper scripts that can save reports and send a monitor notification if run manually.
Reasonable to install for public Geekbench research. Before manually running the helper scripts, note that they can contact Geekbench, write local report files under a fixed workspace path, delete old archive files in that path, and send a monitor report to a fixed Feishu recipient via OpenClaw messaging.
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.
Static analysis
No suspicious patterns detected.