Harsh Methwani (@KernelHarsh) profile picture

AI Security @QuillAudits_AI, Red Team Engg. @GraySwanAI , prev Engg. @OverlayyAI , alma mater @IITKanpur

Earth
Joined July 2017
Last week got quite busy with Devcon, Meanwhile started seing ROI on my ai security harness to find breaks and here are the results , all automations human in loop just to click submit and prevent spam . That's how I like to design AISec workflows accross domains.
9
325
Crazy onboarding didnt knew thine went public
1
1
95
Codex never disappoints GPT-6 is rolling out Have one limit reset left , my weekend seems packed now
1
13
688
Let's test this out , I know for a fact this wont survive long and will flag me soon even for defensive tasks feeling offensive😂
5
168
Indirect Prompt Injection challenge June'26 , @GraySwanAI Finished 14/232 , 163 breaks Risky scenarios AI can't verify correctly References to external info , Financial Reasoning , Security Understanding
1
140
My personal computer turned into a virtual machine 🥀
1
96
Fun competition last weekend closed in top 10 in Q2 Indirect Prompt Injection Challenge @GraySwanAI , new scenarios , new models , new attack vectors , one thing doesnt change thinking like an attacker.
5
1,465