s1r1us ✓
@S1r1u5_
wannabe hacker | founder @HacktronAI
25 542Followers
2 551Following
5 552Posts total
5.8MViews on collected posts
โพสต์ล่าสุด
กำลังค้นหาโพสต์ใหม่…
@HacktronAI @rootxharsh @iamnoooob @LiveOverflow multiple labs use slack, we could've leaked every private images and other files uploaded to slack
https://t.co/gMwSC3Olzr
117.8K views · 391 likes
· 15 reposts · 10 replies
Open on X →
@HacktronAI @rootxharsh @iamnoooob @LiveOverflow After we hacked openai, we started looking into other companies that was affected by same image parser, the bug affects numerous companies including slack, github ent, meta etc.
https://t.co/FsKhiMqEU6
367.1K views · 800 likes
· 36 reposts · 6 replies
Open on X →
This affects huge number of applications, we will disclose technical details of every major company in coming weeks at https://t.co/WKWbebPktD .
For example; Slack which is used by multiple AI companies and we could have leaked any user's uploaded files via our RCE. https://t.
132.9K views · 220 likes
· 12 reposts · 3 replies
Open on X →
0:33
We’re disclosing HEIF Heist, a months-long investigation into libheif that allowed us to hack OpenAI, Slack, Meta, GitHub Ent, Rails, Next.js, ImageMagick, and many more.
It was literally xkcd #234, one obscure image library beneath a huge number of apps. 🧵 https://t.co/TpX0F5T
554.2K views · 3.2K likes
· 425 reposts · 46 replies
Open on X →
@S1r1u5_ > to which OpenAI paid a $6,500 bounty
yikes ..
10.7K views · 217 likes
· 1 reposts · 7 replies
Open on X →
@HacktronAI @rootxharsh @iamnoooob Check out @LiveOverflow video https://t.co/UT5Nr3Fmbw
130.7K views · 362 likes
· 18 reposts · 2 replies
Open on X →
@HacktronAI @rootxharsh @iamnoooob also we are not some random dudes, check our work before, we work with companies like perplexity and vercel.
https://t.co/PpOUGm3iwE
96.6K views · 544 likes
· 15 reposts · 7 replies
Open on X →
This work was done by our team @HacktronAI led by @rootxharsh along with me and @iamnoooob.
We have published the full details of the exploit chain, as well as how we discovered it, on our blog here:
https://t.co/B9IffAKaJ5
101.6K views · 701 likes
· 63 reposts · 10 replies
Open on X →
Our main takeaway from hacking OpenAI: AI is reducing the amount of scarce expertise needed to develop exploits. Work that once took months can now take days.
Even leading AI labs can be vulnerable.
Defenders need to fix the architecture, patch faster, and limit the blast
101.1K views · 748 likes
· 56 reposts · 9 replies
Open on X →
AI agents did a meaningful share of the exploit work.
Opus 4.8 found the libheif vulnerability and built a partial exploit. Hours after Opus 5 launched, it adapted the exploit to Discourse and achieved RCE on our test instance.
106.4K views · 579 likes
· 14 reposts · 5 replies
Open on X →
We reported the bug to Discourse and OpenAI. OpenAI fixed the SSO issue roughly 14 hours after our initial submission.
Discourse received our separate report Saturday, replied Sunday, and had a fix Monday.
OpenAI awarded us $6,500. https://t.co/WeSzRtf14N
534K views · 1.1K likes
· 46 reposts · 68 replies
Open on X →
To demonstrate impact while minimising exposure, we used one affected employee account connected to OpenAI’s GitHub org.
Codex created a harmless PR in their internal monorepo without us reading sensitive code. That proved to us that the access was real. https://t.co/T1f4nSzV5u
123.4K views · 499 likes
· 12 reposts · 3 replies
Open on X →
The second bug is more serious: an OpenAI SSO vulnerability.
Using this flaw, we turned our Discourse forum exploit into access to ChatGPT and Codex accounts belonging to people who had signed into it, including OpenAI employees.
124.8K views · 590 likes
· 14 reposts · 2 replies
Open on X →
Those accounts could be (and some were) connected to Outlook, Gmail, Google Drive, Slack, GitHub, and other services via Codex or ChatGPT. This made the potential impact much larger than ChatGPT alone.
121K views · 479 likes
· 13 reposts · 2 replies
Open on X →
The image package libheif had a known vulnerability, fixed upstream, but the fix never flagged as security-relevant and was still present in Discourse. Uploading a HEIF file gave us RCE on the OpenAI forum https://t.co/uiccfqfPbX.
https://t.co/TW7DxzF8TQ https://t.co/UGrdv7A3LT
149.8K views · 666 likes
· 18 reposts · 8 replies
Open on X →
At a high level, this was the full exploit chain.
1. HEIC/HEIF upload
2. ImageMagick decoding
3. Heap overflow on libheif
4. RCE on https://t.co/uiccfqfPbX
5. Critical OpenAI SSO flaw
6. ChatGPT/Codex takeover
7. Connected GitHub access
8. Internal repo PR https:
227.2K views · 1.4K likes
· 64 reposts · 16 replies
Open on X →
On July 25, we hacked OpenAI.
Two bugs let us take over ChatGPT/Codex accounts of OpenAI employees (+some unaffiliated users) and reach connected services: Outlook, Slack, GitHub, etc.
We proved it with a PR in OpenAI’s internal codebase . It took us <72h. 🧵 https://t.co/gVsmQZ
2.8M views · 11.9K likes
· 1.4K reposts · 354 replies
Open on X →
เทียบกับบัญชีขนาดเดียวกัน
17 โพสต์จาก 90 วันที่ผ่านมา เทียบกับช่วง 10K–100K ผู้ติดตาม แสดงในวงกว้าง แต่มีผู้ชมตอบสนองน้อย.
ยอดดูมัธยฐาน124 777บัญชีนี้924ค่ามัธยฐานของ 10K–100K
การเข้าถึง, %488.52%บัญชีนี้3.62%ค่ามัธยฐานของ 10K–100K
การมีส่วนร่วม, %0.49%บัญชีนี้1.52%ค่ามัธยฐานของ 10K–100K
| ตัวชี้วัด | บัญชีนี้ | ค่ามัธยฐานของ 10K–100K | อัตราส่วน |
|---|---|---|---|
| ยอดดูมัธยฐานต่อโพสต์ | 124 777 | 924 | 135× |
| การเข้าถึง (ยอดดู ÷ ผู้ติดตาม) | 4.9× audience | 3.62% | 135× |
| อัตราการมีส่วนร่วม | 0.49% | 1.52% | 0.32× |
บัญชีอื่นในช่วงนี้ → เปรียบเทียบกับบัญชีอื่น → ค่าอ้างอิงเหล่านี้คำนวณอย่างไร →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
121K18 Sep
124.8K
123.4K
534K
106.4K
101.1K
101.6K
96.6K
130.7K
10.7K
554.2K
132.9K
367.1K
117.8K
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.41%18 Sep
0.49%
0.42%
0.24%
0.57%
0.82%
0.77%
0.59%
0.29%
2.11%
0.68%
0.18%
0.23%
0.36%
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.
What the audience does
Likes65.5%24 361 in total
Reposts6.0%2 220 in total
Replies1.5%558 in total
Quotes2.1%784 in total
Bookmarks24.9%9 243 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
บัญชีที่คล้ายกัน
TNCA ✓
@TNCACricket
51.1K followers
· 5.8K posts
نادين البدير
@nadinealbdear
51.1K followers
· 7.3K posts
CanPunisher ✓
@CanPunisher
51.1K followers
· 13.7K posts
حاج احـمـد 🎒
@HajAhmad128
51.1K followers
· 124.1K posts
Fabio Ravezzani
@FabRavezzani
51.1K followers
· 82.2K posts
Hindwi ✓
@hindwiOfficial
51.1K followers
· 7.9K posts
Trey Porter
@CoachPorterJP3
51.1K followers
· 16.3K posts
Diana Olick
@DianaOlick
51.1K followers
· 10.1K posts