MLSecOps Practical Reference Guide, open-source AI and ML security handbook.
-
Updated
Nov 11, 2026 - Python
MLSecOps Practical Reference Guide, open-source AI and ML security handbook.
Pack de Scripts Para Pentesting Inicial a Chatbots
Open-source LLM red teaming framework. Security-test any model (Claude, GPT, Llama) for prompt injection, data leakage, etc. 15 probes, 29 prompt converters, LLM-as-judge grading, adaptive red teaming, static code audit. SARIF + JUnit for CI/CD.
AstrBot + NapCat/OneBot policy plugins, deployment templates and optional integrations
canaryprobe: deterministic, zero-dependency checks for system-prompt leaks, secret leaks, prompt injection and unconfirmed tool calls in your own chatbot (OWASP LLM Top 10, SARIF for CI)
Provide a Python-native framework to test and audit security in large language models with coverage of key OWASP LLM risks.
Interactive OWASP LLM guardrail lab comparing unprotected and protected LLMs with evidence, output scanning, and red-team validation.
Prompt injection scanner for LLM apps and AI chatbots — red team your own AI before someone else does. Stdlib-only Python, one-file HTML report, OWASP LLM Top 10.
Versioned prompt-injection test harness: fires 40+ attacks at any chatbot and scores them objectively. Ships a vulnerable vs hardened demo bot (100% → 2.4% ASR) with 8 toggleable defense layers.
🔒 Safeguard LLM behavior with PromptGuard to detect unseen regressions and ensure reliable outputs amid evolving model updates.
To associate your repository with the chatbot-security topic, visit your repo's landing page and select "manage topics."