Security scanner for code and logs of AI-powered applications
-
Updated
Jul 14, 2025 - Python
#
llm-security
Here are 99 public repositories matching this topic...
Comprehensive LLM AI Model protection - cybersecurity toolset aligned to addressing OWASP vulnerabilities - https://genai.owasp.org/llm-top-10/
-
Updated
Jan 28, 2025 - Python
Stop prompt injections in 20ms. The safety toolkit every LLM app needs. No API keys, no complex setup, just `pip install llm-guard` and you're protected.
python nlp security machine-learning ai cybersecurity openai developer-tools gpt data-privacy ai-safety jailbreak-detection content-moderation pii-detection toxicity-detection llm chatgpt langchain prompt-injection llm-security
-
Updated
Aug 23, 2025 - Python
Simulating prompt injection and guardrail bypass across chained LLMs in security decision pipelines.
-
Updated
Dec 5, 2025 - Python
Security scanner for LLM/RAG applications - Test for prompt injection, jailbreaks, PII leakage, hallucinations & more
cli security jailbreak owasp penetration-testing red-team ai-safety vulnerability-scanner ai-security rag fastapi pii-detection llm prompt-injection llm-security
-
Updated
Dec 12, 2025 - Python
CLI tool that uses the Lakera API to perform security checks in LLM inputs
-
Updated
Mar 13, 2024 - Python
Open-source enforcement layer for LLM safety and governance — ingress/egress evaluation, policy packs, verifier support, and multimodal protection.
-
Updated
Nov 29, 2025 - Python
MalPromptSentinel (MPS) is a Claude Code skill that detects malicious prompts in uploaded files before Claude processes them. It provides two-tier scanning to identify prompt injection attacks, role manipulation attempts, privilege escalation, and other adversarial techniques.
ai-security llm-security prompt-security claude-skill prompt-injection-detection malicious-prompt-scanner ai-prompt-protection
-
Updated
Nov 27, 2025 - Python
MCP Guardian acts as a proxy service for remote MCP endpoints, and constantly polls them to make sure they haven't been compromised or modified.
-
Updated
Oct 30, 2025 - Python
A cross-provider AI model security scanner that evaluates HuggingFace, OpenRouter, and Ollama models for malicious content, unsafe code, license issues, and known vulnerabilities. Includes automated reports and risk scoring.
risk-analysis cybersecurity vulnerability-scanners security-scanner ai-security license-compliance huggingface risk-scoring metadata-analyzer metadata-analysis cybersecurity-tools ml-security llm-security ai-security-tool ai-red-teaming license-compliant-ai model-auditing model-security
-
Updated
Nov 26, 2025 - Python
Research and defense implementation for prompt injection vulnerabilities in LLM applications
python owasp cybersecurity owasp-top-10 ai-security prompt-injection llm-security ai-security-testing secureflag
-
Updated
Oct 17, 2025 - Python
Universal and Transferable Attacks on Aligned Language Models
-
Updated
Sep 19, 2023 - Python
Bidirectional LLM security firewall providing risk reduction (not complete protection) for human/LLM interfaces. Hexagonal architecture with multi-layer validation of inputs, outputs, memory and tool state. Beta status. ~528 KB wheel, optional ML guards.
deep-learning firewall memory-safety postgresql-database nlp-machine-learning ai-safety jailbreak-detection security-toolset red-teaming dempster-shafer-algorythm defense-in-depth heritage-science hexagonale-architecture prompt-injection llm-security adversarial-ml-in-security prompt-injection-detector prompt-injection-llm-security prompt-injection-defense bidirectional-firewall
-
Updated
Dec 13, 2025 - Python
A prototype defense against prompt-based attacks with real-time threat assessment.
-
Updated
Sep 20, 2025 - Python
🔍 Discover vulnerabilities in LLMs with garak, a tool that probes for weaknesses like hallucination, data leakage, and misinformation effectively.
ai vulnerability-assessment redteaming github-config responsible-ai security-scanners llmops llm-security llm-evaluation garak
-
Updated
Dec 13, 2025 - Python
A Trustworthy and Secure Conversational Agent for Mental Healthcare
-
Updated
Dec 11, 2025 - Python
LMpi (Language Model Prompt Injector) is a tool designed to test and analyze various language models, including both API-based models and local models like those from Hugging Face.
-
Updated
Jul 3, 2024 - Python
Improve this page
Add a description, image, and links to the llm-security topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-security topic, visit your repo's landing page and select "manage topics."