Krishna Sharma (@Krishna14u) profile picture

AppSec | Senior Application Security Engineer@Coursera

Indore, India
Joined May 2016
Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)Photo by Krishna Sharma (@Krishna14u)
Krishna Sharma retweeted
Added more items for August 2026 in webhacklist.com/. I think by the time @albinowax ask us for a list in 2027, it should have some good things in it already, but I am sure we are still missing some links! Please contribute if you can & don't let 🤖 judges us alone 🤭
3
14
111
6,095
Krishna Sharma retweeted
AI may make intelligence abundant. It will not make attention automatic. economicsofai.substack.com/p…
1
4
1,035
Krishna Sharma retweeted
Really interesting research from Anthropic on using multi-agent systems for vulnerability research: anthropic.com/research/multi… Their collaborating agents found 266 vulnerabilities vs 21 for independent agents. But the part I found most interesting is that only 12 findings overlapped. Feels like another sign that the future of AI auditing probably isn’t just running one really strong model over a codebase. Different agents, different prompts, and different ways of exploring the code seem to find very different things. I think the best systems will eventually look much more like an actual audit team: multiple agents exploring independently, sharing leads, specializing in certain areas, and then having other agents try to disprove the findings. I've also been experimenting a lot with multi-agent models, assigning different roles and incentives, which has led to huge improvements. The crazy part is, @muellerberndt did this already a year ago with his AI auditing system Hound.
11
46
3
359
30,484
Krishna Sharma retweeted
This was a great read, Stellar work @0xLupin
“Security researchers are doomed because of AI.” I kept hearing versions of this, so I went back through 500 years of people saying the same thing every time a machine learned a human skill. Some were idiots. Some were right. Here’s where I landed.
3
37
284
55,750
Krishna Sharma retweeted
Release Black Hat USA 2026 Slides · onhexgroup/Conferences · GitHub github.com/onhexgroup/Confer…
5
141
4
556
29,584
Krishna Sharma retweeted
Missed DEFCON 34? Here you go with all slides and content: media.defcon.org/DEF%20CON%2…
6
156
1
690
40,309
Krishna Sharma retweeted
In the last years I wrote up what I learnt from doing two companies, zynamics and optimyze. It is still work-in-progress, but it is ~27 pages, and I think helpful for everybody that is considering starting a company: thomasdullien.github.io/guid…
9
42
2
274
18,933
I am looking for awesome research on hacking MCP servers. If you have any, let me know.
6
14
122
12,566
Krishna Sharma retweeted
Excellent high level walkthrough of how LLMs work (@0xkato) 0xkato.xyz/how-llms-actually… #infosec
3
39
247
11,484
Krishna Sharma retweeted
How to use LLMs for vulnerability research by @0xAsm0d3us devansh.bearblog.dev/needle-… #infosec #llm
2
70
399
20,926
Krishna Sharma retweeted
Do you watch Netflix in your free time? Try hackflix for security conference talks h4ckfl1x.com/ #cybersecurity #bugbounty
18
321
9
1,703
79,692
Krishna Sharma retweeted
LLMs for vulnerability research by @0xAsm0d3us devansh.bearblog.dev/needle-… #infosec #llm
51
234
14,830
I completed the Web Security Academy lab: Bypassing access controls using email address parsing discrepancies, Thanks @garethheyes for the amazing CTF challenge. @WebSecAcademy portswigger.net/web-security…
2
6
692