No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by asgeirtj · Codex Skill · ★ 69.4k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is system_prompts_leaks safe to install? View the security audit →
System Prompts Leaks Extracted system prompts, system messages, and developer instructions from popular AI chatbots and coding assistants — ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, Gemini CLI), Grok (4.2, 4), Perplexity, and more. Updated regularly with new models and versions. PRs welcome. Anthropic — Claude [S
| Stars | 69,432 |
| Forks | 11,292 |
| Language | Python |
| Category | Codex Skill |
| License | CC0-1.0 |
| Quality Score | 53.9108758450605/100 |
| Open Issues | 56 |
| Last Updated | 2026-10-12 |
| Created | 2025-05-03 |
| Platforms | claude-code, codex, gemini, python |
| Est. Tokens | ~15k |
These tools work well together with system_prompts_leaks for enhanced workflows:
Looking for a system_prompts_leaks alternative? If you're comparing system_prompts_leaks with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Pr
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w
The agent engineering platform.
Agent skill that removes signs of AI-generated writing from text
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure,
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answer
Explore other popular codex skill tools:
system_prompts_leaks is Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Gro. It is categorized as a Codex Skill with 69.4k GitHub stars.
system_prompts_leaks is primarily written in Python. It covers topics such as ai, ai-agents, ai-prompts.
You can find installation instructions and usage details in the system_prompts_leaks GitHub repository at github.com/asgeirtj/system_prompts_leaks. The project has 69.4k stars and 11292 forks, indicating an active community.
system_prompts_leaks is released under the CC0-1.0 license, making it free to use and modify according to the license terms.
The top alternatives to system_prompts_leaks on Agent Skills Hub include ai-guide, repomix, langchain. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: