Personal AI
Security checks across malware telemetry and agentic risk
Overview
This skill coherently connects Codex to Personal AI through OOMOL, with disclosed write actions and no evidence of hidden or malicious behavior.
Before installing, understand that this skill can add messages, memories, documents, and URL content to your Personal AI account when you approve write actions. Use it only if you trust OOMOL as the connector provider and are comfortable installing/signing into the `oo` CLI if it is not already set up.
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
63/63 vendors flagged this skill as clean.
