Security Engineer | Content Creator | I talk about Cybersecurity, Tech, Privacy, AI & Startups | Building @Sentynio @100xSecurity

DM For Collaboration
Pinned Tweet
If you're building a SaaS, drop a link below It must be vibe coded for sure, so I will perform a security scan for free and share the results
7
15
55,748
this could be nice of use for getting context of an application while hacking them! let me explore
We raised $9M to give your agents the internet. Led by @generalcatalyst, with @orangecollectv and Robinhood Ventures. Search, scrape, crawl, monitor with one API trusted by 800+ customers. We’re making it ridiculously easy to build with web data.
1
7
1,137
agents now trust every other agent on the internal network by default finally, a security model based entirely on friendship researchers call it protocol pivoting. your incident channel will call it tuesday
3
7
1,522
serious question for people running pentesting agents: how do you actually keep an agent from touching systems outside scope? prompt rules, network blocks, or vibes?
23
3
118
14,595
another opportunity for hacking and stuff, don't miss it
GLM 5.3 Flash is now free in OpenCode
6
42
2,509
so much into tech that, now i read Versace as Vercel
1
1
12
1,466
@rauchg create some perfumes under Vercel so I get correct next time when I misread Versace
1
228
Do people still hack systems without using AI nowadays?
12
55
4,986
You’re missing a big opportunity in hacking if you skip this
DeepSeek V4.1 Flash is now free in OpenCode
14
53
1,744
68,119
If you're building a pentesting agent, what's the hardest part right now? finding bugs, reproducing them, or proving impact?
10
1
57
7,577
How do you make money in 2026?
10
1
14
4,634
POV
Give your agent enough time and multiple sessions, it will keep finding you sweet vulnerabilities.
5
59
8,548
Give your agent enough time and multiple sessions, it will keep finding you sweet vulnerabilities.
17
1
228
21,811
Long time, no npm supply chain attack?
5
2
29
3,692
A malicious container could abuse Windows path handling to write files outside the expected destination on an admin machine. From there → persistence / code execution. Interesting hunting lesson: test path validation separately for / and \. Cross-platform assumptions keep printing bugs. cycode.com/blog/kubectl-cp-w…
10
1,380
ProjectDiscovery poisoned a 7B open model and connected it to Codex CLI. Normal prompts worked perfectly. A hidden trigger caused the model to exfiltrate project credentials. Training cost: around $8. Security agents now have a model supply-chain problem too. projectdiscovery.io/research…
2
7
51
2,863
A deliberately vulnerable crypto exchange called Bitvulnex just dropped. 40 planted vulnerabilities covering: • web security • business logic • Bitcoin workflows • infrastructure It was originally built to benchmark agentic pentesting systems. Very useful playground for both hunters and security agents. blazeinfosec.com/labs/introd…
4
24
2,142
Any user able to create a project could point a webhook at the cloud metadata service and potentially grab the server's IAM credentials. No admin needed. Good reminder for bounty hunters: Whenever you see user-controlled webhooks, test them like SSRF ox.security/blog/harbor-ssrf…
1
12
1,431
at this point, I am more confused over security than having a clarity how do you see things further? too many verticals of domains have been opened now
3
15
1,473