Security audit
OATDA List Models
Security checks across malware telemetry and agentic risk
Overview
This skill only lists OATDA models using a disclosed OATDA API key and does not install code or change the user's system.
Before installing, make sure you trust OATDA and use an API key with only the access needed. Keep ~/.oatda/credentials.json protected, and do not ask the agent to print or share the full API key.
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.