Top 10 GitHub Repos for Prompt-Injection & LLM Red-Team Work, October 4 2025
Short intro (one line)
A snapshot of the most useful GitHub projects for prompt-injection, jailbreaks, detection and red-team automation — stars, recency, and practical notes included. (GitHub)
Ranked table — top 10 (prompt-injection topic)
Rank | Repo (link) | Stars | Last updated | Short notes |
---|---|---|---|---|
1 | asgeirtj / system_prompts_leaks | 21.8k | Updated Oct 4, 2025 | Large collection of extracted system prompts from ChatGPT, Claude, Gemini — high-value payloads for red-team tests and analysis. (GitHub) |
2 | CyberAlbSecOP / Awesome_GPT_Super_Prompting | 3.1k | Updated Sep 25, 2025 | Curated jailbreaks, prompt leaks, templates and attack examples — great “attack library.” (GitHub) |
3 | protectai / llm-guard | 2.1k | Updated Sep 29, 2025 | Runtime toolkit for detecting/sanitizing malicious prompts — useful as a runtime guard layer. (GitHub) |
4 | microsoft / AI-Red-Teaming-Playground-Labs | 1.7k | Updated Aug 14, 2025 | Hands-on labs and scenarios from Microsoft for building red-team skills and infrastructure. Good for structured training. (GitHub) |
5 | abilzerian / LLM-Prompt-Library | 1.5k | Updated Jul 12, 2025 | Playgrounds and templating for experimental prompts — useful for building reproducible payloads. (GitHub) |
6 | protectai / rebuff | 1.4k | Updated Aug 7, 2024 | Prompt injection detector (prompt scanner) — complementary to llm-guard for detection pipelines. (GitHub) |
7 | utkusen / promptmap | 986 | Updated Sep 30, 2025 | Security scanner for custom LLM apps; helpful for assessing deployed prompt flows. (GitHub) |
8 | whylabs / langkit | 948 | Updated Nov 22, 2024 | LLM observability toolkit — extracts signals from prompts/responses for monitoring and safety checks. (GitHub) |
9 | tldrsec / prompt-injection-defenses | 556 | Updated Feb 22, 2025 | Consolidated list of practical and proposed defenses — excellent starting point for countermeasure design. (GitHub) |
10 | deadbits / vigil-llm | 416 | Updated Jan 31, 2024 | Detector for prompt injections, jailbreaks and risky inputs — useful lightweight scanner for pipelines. (GitHub) |
(Source: GitHub prompt-injection
topic listing — validated metadata: stars & last-updated shown on each repo card.) (GitHub)
Quick summary & recommended first steps
- Mirror the top repos locally (system_prompts_leaks, Awesome_GPT_Super_Prompting) to assemble attack payloads. (GitHub)
- Run detection tools (llm-guard, rebuff, vigil-llm) in a sandboxed environment against your prompt flows. (GitHub)
- Automate via CI: add prompt-fuzzing and observability (use prompt datasets + langkit) and baseline with curated defenses (tldrsec). (GitHub)
Caveats & safety note
- Many repos contain dual-use payloads and extracted system prompts. Do not run untrusted code or use extracted prompts against production systems. Sandbox, vet, and isolate all tests. (GitHub)
FEATURED TAGS
computer program
javascript
nvm
node.js
Pipenv
Python
美食
AI
artifical intelligence
Machine learning
data science
digital optimiser
user profile
Cooking
cycling
green railway
feature spot
景点
work
technology
F1
中秋节
dog
setting sun
sql
photograph
Alexandra canal
flowers
bee
greenway corridors
programming
C++
passion fruit
sentosa
Marina bay sands
pigeon
squirrel
Pandan reservoir
rain
otter
Christmas
orchard road
PostgreSQL
fintech
sunset
thean hou temple in sungai lembing
海上日出
SQL optimization
pieces of memory
回忆
garden festival
ta-lib
backtrader
chatGPT
stable diffusion webui
draw.io
streamlit
LLM
AI goverance
prompt engineering
fastapi
stock trading
artificial-intelligence
Tariffs
AI coding
AI agent
FastAPI
人工智能
Tesla
AI5
AI6
FSD
AI Safety
AI governance
LLM risk management
Vertical AI
Insight by LLM
LLM evaluation
AI safety
AI Governance
Privacy & Data Protection Compliance
Microsoft
Scale AI
Claude
Anthropic
新加坡传统早餐
咖啡
Coffee
Singapore traditional coffee breakfast
Quantitative Assessment
Oracle
OpenAI
Market Analysis
Dot-Com Era
AI Era
Rise and fall of U.S. High-Tech Companies
Technology innovation
Sun Microsystems
Bell Lab
Agentic AI
McKinsey report
Dot.com era
AI era
Speech recognition
Natural language processing
Privacy
Google
Enterprise AI
Nvdia
AI cluster
COE
Singapore
Shadow AI
AI Goverance & risk
Tiny Hopping Robot
Robot
Materials
SCIGEN
RL environments
Reinforcement learning
Continuous learning
Google play store
AI strategy
Model Minimalism
Fine-tuning smaller models
LLM inference
Closed models
Open models
Privacy trade-off
MIT Innovations
Federal Reserve Rate Cut
Mortgage Interest Rates
Credit Card Debt Management
Investor Sentiment
Enterprise AI adoption
AI Innovation
AI Agents
AI Infrastructure
Generative AI
Workslop
Federal Reserve
Multimodal AI
Government Shutdown
AI Fine-Tuning
LLMOps
Frontier Models
Hugging Face
Multimodal Models
Energy Efficiency
AI infrastructure
Semiconductors
Gold & index inclusion