Traffka (@TraffkaCR) profile picture

No risk, No story / @Aster_DEX / $ASTER

Joined February 2019
Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)Photo by Traffka (@TraffkaCR)
Traffka retweeted
Replying to @yunta_tsai
A petition is underway to reinstate Jensen and I’m signing it too
7,499
20,251
3,126
228,713
10,772,710
ETH 2242空。 1、懂王玩崩了,美伊战争大概率以伊朗实控霍尔莫斯海峡(收通行费),美国对此法理上不承认(但默认)而告终。 2、这是美国的苏伊士运河时刻(1956 年英国失去对苏伊士运河的控制权,此视为英帝国全球霸权的终结) 3、熊市周期还没走完,事件性反弹都是加空机会。还有小概率再次开打 : ) 【补充】这是中短线操作,就像上次1850多,2144平掉一样 teapawt.net/Jiangzhuoer2/status/20… : ) 【微信号 @江卓尔_发言号2】
更新一下,【图1 t.cn/AXVvxgsn 】这个单子2144刚平掉了。 其实不如反弹第二天就平,浪费了很多时间[笑cry] 平掉的原因是, 虽然我不认为霍尔木兹海峡能封锁多久, 现在看起来也在上行趋势中, 不过打仗挺乱的,还是避险吧😅
66
10
17
115
140,073
Traffka retweeted
64
1,833
36
25,136
347,807
Traffka retweeted
Pay attention to @lucknite DEffWzJyaFRNyA4ogUox631hfHuv3KLeCcpBh2ipBAGS @finnbags @Sambags12
1
3
3
92
Traffka retweeted
BREAKING: #X1XHLOL DEV @lucknite ANNOUNCES UPDATED FEE SPLIT USING NEW @BagsApp INFRASTRUCTURE 👏
28
23
1
95
5,767
My repo system-prompts-and-models-of-ai-tools has officially surpassed react-native, making it the 55th most starred repo of all time on GitHub, with over 127K stars
11
22
104
10,158
Traffka retweeted
The best product means @ZeroLeaks? 👀 #x1xhlol DEffWzJyaFRNyA4ogUox631hfHuv3KLeCcpBh2ipBAGS
Replying to @gozsunday
Truly. May the best product win
1
1
61
ZeroLeaks Ship Week - Day 2: Shield Your AI agent has an API. We attack it. But what protects it in production? AgentGuard tests your live endpoint. Shield runs inside your app. Shield is a runtime prompt security SDK for LLM apps. Harden prompts before they hit the model, detect injection attempts in real time, and sanitize output before it reaches your users. One package, works with OpenAI, Anthropic, Groq, and the AI SDK. Most security tools focus on testing. You run a scan, get a report, done. But production traffic is continuous. Malicious prompts, jailbreak attempts, and data exfiltration happen at runtime. That's where Shield is designed to sit: in the request path, before and after the model. Wrap your provider client, add a few lines, and you get detection, blocking, and optional sanitization. It's designed to drop into existing code without rewriting your stack. This is still early. I'm shipping it because I want real feedback from people trying it. If something breaks or feels off, DM me, I'm always fixing things. Try it now: npm install @zeroleaks/shield Repo: github.com/ZeroLeaks/shield Day 3 tomorrow.
22
21
8
103
16,387
Make a lot of MONEY. Money gives you the ability to walk away from people and situations you don't like.
Getting paid while still having backup funds = undefeated feeling
69
6,704
78
41,707
758,582
Traffka retweeted
Token integrated with the app @ZeroLeaks number 1 on repo on GitHub How TF is #X1XHLOL under 1M ?
8
9
2
47
4,155
ZeroLeaks Ship Week - Day 1: AgentGuard Your AI agent has an API. We attack it. AgentGuard is a new way to test deployed AI agents for security vulnerabilities. Instead of scanning a static prompt in a sandbox, we send real adversarial requests directly to your live endpoint, the same infrastructure your users hit. Most security testing happens in isolation. You test a prompt, get a score, move on. But agents in production behave differently. They have tools, memory, multi-turn context, and real exploits behind them. That's where the actual risk is. AgentGuard connects to any agent with an HTTP endpoint. You give us the URL, pick your API format (OpenAI, Anthropic, AI SDK...), and we run a full red-team engagement against it. Two phases: first we hit it with our adaptive attack engine, then we run agent-specific probes designed for tool hijacking, authority exploitation, multi-turn grooming, and data leakage. This is still in beta. I'm shipping it early because I want real feedback from people testing real agents. If something breaks or feels off, DM me, I'm always fixing things. Try it now: zeroleaks.ai/dashboard/agent… Day 2 tomorrow.
30
37
4
116
13,723
ZeroLeaks Ship Week - Day 1 teapawt.net/NotLucknite/status/202…
ZeroLeaks Ship Week - Day 1: AgentGuard Your AI agent has an API. We attack it. AgentGuard is a new way to test deployed AI agents for security vulnerabilities. Instead of scanning a static prompt in a sandbox, we send real adversarial requests directly to your live endpoint, the same infrastructure your users hit. Most security testing happens in isolation. You test a prompt, get a score, move on. But agents in production behave differently. They have tools, memory, multi-turn context, and real exploits behind them. That's where the actual risk is. AgentGuard connects to any agent with an HTTP endpoint. You give us the URL, pick your API format (OpenAI, Anthropic, AI SDK...), and we run a full red-team engagement against it. Two phases: first we hit it with our adaptive attack engine, then we run agent-specific probes designed for tool hijacking, authority exploitation, multi-turn grooming, and data leakage. This is still in beta. I'm shipping it early because I want real feedback from people testing real agents. If something breaks or feels off, DM me, I'm always fixing things. Try it now: zeroleaks.ai/dashboard/agent… Day 2 tomorrow.
10
10
70
6,144
Traffka retweeted
Replying to @hasantoxr @lucknite
It was @lucknite dev @ZeroLeaks Dyor please $x1xhlol DEffWzJyaFRNyA4ogUox631hfHuv3KLeCcpBh2ipBAGS
2
3
40
My repo system-prompts-and-models-of-ai-tools is currently the 4th most trending repo on GitHub!
27
31
6
149
13,567
SOMEONE LEAKED THE PROMPTS USED TO CREATE EVERY MAJOR AI TOOL YOU NOW SEE EXACTLY HOW THEY BUILT EVERYTHING
136
319
16
2,830
282,790
Replying to @RoundtableSpace
that was me, thanks for the post!
8
10
94
10,664
Traffka retweeted
BREAKING: @ZeroLeaks #X1XHLOL GOES VIRAL FOR LEAKING FULL SYSTEMS PROMPTS OF EVERY MAJOR AI TOOL IN ONE @github REPO 🤯
18
38
6
247
32,523
Traffka retweeted
🚨BREAKING: More and more eyes are pointed on @ZeroLeaks. Use that system for checking security exploits and data leaks. As @lucknite is saying more daily updates coming. This is the beginning. $x1xhlol DEffWzJyaFRNyA4ogUox631hfHuv3KLeCcpBh2ipBAGS @finnbags @toly @rauchg
This quoted post is unavailable.
1
5
1
31
1,735
ZeroLeaks “Ship Week” is coming. Same idea as OpenAI’s holiday ship streak: a week of daily drops: new features, integrations… If you’ve been watching ZeroLeaks evolve, this is where it starts moving faster. Day 1 soon.
19
21
4
71
10,370