Pydantic Ai Model Integration
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only PydanticAI model configuration guide with expected examples for provider selection, API keys, streaming, fallbacks, and usage limits.
Installers should treat this as a normal documentation skill, but should keep real provider API keys in environment variables or a secret store, avoid committing credentials, and review provider data-handling policies before sending sensitive prompts.
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.