ZenGuard AI
ActiveDescription
The fastest Trust Layer for AI Agents with prompt injection detection, PII filtering, and content safety guardrails.
Related Projects
Pytector
40 · Python
Easy to use LLM prompt injection detection and prompt input sanitization Python package with multiple detection methods and custom rules.
prompt-injectiondetectionsanitization +2
AegisGate
34 · Python
Open-source security gateway for LLM APIs with prompt injection detection, PII redaction, dangerous response filtering, and more.
llm-securitygatewayprompt-injection +2
LLM Security Prompt Injection
62 · Jupyter Notebook
Research project investigating LLM security by performing binary classification for prompt injection attack detection and analysis.
prompt-injectionllm-securityclassification +2
Pydantic AI Shields
49 · Python
Guardrail capabilities for Pydantic AI including cost tracking, prompt injection detection, PII filtering, and safety validation.
pydantic-aiguardrailscost-tracking +2