#javascript #ai #anthropic #chatbots #chatgpt #claude #gemini #generative_ai #google_deepmind #large_language_models #llm #openai #prompt_engineering #prompt_injection #prompts

There is a collection of system prompts used by popular chatbots like ChatGPT and others. These prompts are instructions that guide how chatbots respond. They are now available publicly on GitHub, which can be very helpful for users. By seeing these prompts, users can understand how chatbots work and even learn how to create their own AI tools. This can help developers build better AI applications and improve their understanding of AI technology.

https://github.com/asgeirtj/system_prompts_leaks

#python #agent_security #ai_agents #ai_security #benchmark #claude #claude_code #codex #cursor #llm_security #mcp #model_context_protocol #prompt_injection #threat_detection

ADR is an enterprise security system for AI agents that watches what agents do, tests them for attacks, detects risky behavior, and is being used in production at Uber; its paper was accepted to MLSys 2026. The benefit to you is better protection for AI tools like Cursor, Claude Code, and Codex, plus a way to find unsafe actions before they cause harm.

https://github.com/uber/ADR

#python #agent #agent_security #ai_infra #ai_red_teaming #ai_security #llm #llm_evaluation #llm_jailbreak #llm_security #mcp_scan #openclaw_security #prompt_injection #prompt_security #scanner #security #security_tools #skill_scanner #skills_security #vulnerability

A.I.G (AI-Infra-Guard) is a Tencent Zhuque Lab tool for AI red teaming and security checks. It scans AI infrastructure, MCP servers, agent skills, and jailbreak risks, and it can run with Docker, a web UI, or an API. This helps you find weak points early, understand real security risks, and fix problems before they affect your AI systems.

https://github.com/Tencent/AI-Infra-Guard