Threat Intelligence for the AI Ecosystem
- Tweets 21
- Following 53
- Followers 206
- Likes 46
Big night ahead, Demo Day is here! π
Weβre presenting NovaHunting tonight as part of the Winter 26 @startmate cohort. Massive thanks to everyone who helped us get ready over the last few months!
π The Timber Yard, Melbourne
ποΈ Tonight @ 6PM
ποΈ Tickets: luma.com/DemoDay-W26
1
1
57
Melbourne, @fr0gger_ is in town! π¦πΊ
After his #CyberCon talk today, he's staying until @startmate Demo Day on 19 Oct π
Security teams, founders, investors: want to meet him and see NovaHunting in action? DM us for a coffee or a demo β
#AIsecurity #NovaHunting #ThreatIntel
1
1
2
1,074
AI agents read data, call tools, and take action, making them prime targets for attackers.
NovaHunting stops prompt injections, hijacking, and data leaks while keeping you in total control:
βοΈ Custom detection rules
ποΈ Full visibility into actions
π Integrates with your stack
1
2
81
Meet us at #CyberCon2026 Melbourne.
@fr0gger_ will be sharing practical insights on AI threat intelligence.
π€ βYour AI threat intelligence is broken. Here is what works.β
π
Thu 15 Oct | 4:40β5:20 PM
π Melbourne
1
3
1,100
Your AI agent has access to your data... but who else is giving them instructions? π
Adversarial prompts and unauthorised actions are the new attack surface. NovaHunting blocks them before they run.
Want to see it in action? Book a demo with us!
1
3
136
AI is changing threat intelligence. Is your team keeping up? π
Our in-depth AI security training is coming to π© Black Hat Europe, London, 7-10 Dec.
ποΈ Seats are limited: blackhat.com/europe/trainingβ¦
π’ Private in-house sessions available, DM us.
1
76
Most rely on AI for faster exploitation, but the real risk is securing the AI stack: agents, MCP servers, and supply chains.
β‘ SecurityBreak built NovaHunting to give your team full AI visibility, threat detection, and proactive hunting.
βοΈ Book a demo: securitybreak.io/novahunting
1
5
79
SecurityBreak retweeted
π€ Tomorrow I will be at @UnpromptedAU to talk about AI Threat Intelligence!
I will be presenting on the current threats targeting the AI ecosystem and showing you the work we are doing at @SecurityBreakAI to operationalize this type of threat in your own pipeline!
1
5
30
1,588
SecurityBreak retweeted
π€ I just published a short video about PromptIntel, the threat intelligence feed for AI.
PromptIntel is an open database that tracks adversarial prompts observed in attacks. The goal is to identify prompts that attackers actively use in their operations.
π₯ piped.video/Ids__t2jOdk
4
20
59
4,698
10 days, 2 courses to teach, and non-stop cyber! β‘οΈ
@fr0gger_ is representing Security Break at Black Hat USA & DEF CON.
Heβll be delivering two deep-dive trainings, then hitting the conference track and community events.
Slide into his DMs to connect while heβs there! π©
1
5
2,239
"A no-bullshit AI security training." π₯
The best feedback is knowing teams leave with practical frameworks, learning not just what AI tech exists, but how to safely integrate it into their daily workflows.
π¨ Last chance to book at Black Hat USA (link in comments)! π
1
2
6
841
π
Secure your spot:
β‘οΈ Session 1 (August 1 - 2): blackhat.com/us-26/training/β¦
β‘οΈ Session 2 (August 3 - 4): blackhat.com/us-26/training/β¦
2
4
111
β‘οΈFind the break before the breach with SecurityBreak.
As AI agents & workflows expand, so does the attack surface. We provide AI threat intelligence & detection to keep your AI ecosystem secure.
Explore NovaHunting,
Read SecurityBreak Research.
2
5
636
SecurityBreak retweeted
π§ @SecurityBreakAI Research has just published a threat report, authored by @pedrinazziM that explores how attackers are currently abusing HTTP headers to target AI systems and agents!
Specific HTTP headers can be exploited and Marco classifies these attacks into 16 categories ranging from data destruction to deterring AI agents.
Find out more in our latest research! π
blog.securitybreak.io/the-paβ¦
12
33
2,750
π¨ Black Hat USA 2026 is just 2 weeks away!
Join Thomas Roccia (@fr0gger_) for our 2-day intensive training: "Practical AI for Threat Intelligence".
Master AI agents and level up your team's threat hunting. Seats are filling up fast! π€
π Links to sessions in the comments!
1
2
2,207
π
Secure your spot before they sell out:
β‘οΈ Session 1 (August 1 - 2): blackhat.com/us-26/training/β¦
β‘οΈ Session 2 (August 3 - 4): blackhat.com/us-26/training/β¦
75
SecurityBreak retweeted
π€ Last month, we ran another AI for Threat Intelligence training in Sydney. We filmed a few behind-the-scenes moments and some testimonials to show what the course is all about.
We will be at @BlackHatEvents next month and there are still a few seats available.
π₯ piped.video/sNghLilt3bs
1
5
37
4,759