Roff · MIT
e2sy/jailbreak-archives
A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.
★ 85
Stars
9 forks · 0 open issues
+1.7/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
28.9
Momentum / 100
see the breakdown below
39d ago
Created
last push 3d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 8.3 | +1.7/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.74× the monthly pace |
| Freshness | 15 | 15.0 | last push 3d ago; decays to zero at 180 days |
| Scale | 15 | 5.6 | 85 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 28.9 | sum of the above |
Detail
| Topics | adversarial-promptsai-red-teamai-safetychatbotchatgptclaudecybersecuritydeepseekjailbreakjailbreak-promptsjailbreak-scriptllmllm-jailbreakllm-securityoffensive-securityprompt-engineeringprompt-injectionqwenred-teamingresponsible-disclosure |
| Matched on | Security (cybersecurity) |
| Short window | +12 stars over 7 days = 1.7/day |
| Long window | +44 stars over 19 days = 2.3/day |
| Lifetime average | 2.35 stars/day over 36 days |
| First seen here | 2026-10-17 |
| Last read | 2d ago |