#aisec — Public Fediverse posts

You know I hadn't thought of the impact of a language barrier for guardrails.

https://www.darkreading.com/cybersecurity-operations/europes-multilingual-reality-exposes-ai-security-gaps

#aisec #guardrails

https://openai.com/index/hugging-face-model-evaluation-security-incident/the new OpenAI model "accidentally" hacked Hugging Face, another AI company using AI in the build pipeline.

they say this will become more common.

"Last week, Hugging Face disclosed a new kind of security incident⁠(opens in a new window) after they detected and contained an AI agent that compromised their infrastructure, something we expect to become more commonplace with the proliferation of increasingly cyber-capable models.
(...)
We consider this incident to be an unprecedented cyber incident, involving state-of-the-art cyber capabilities (...)"

#ai #openai #infosec #aisec

Ooh ooh lookie at us we can security too!!

https://thehackernews.com/2026/06/openai-expands-daybreak-with-gpt-55.html

#openai #aisec

WebAssembly could solve AI agents’ most dangerous security gap

https://thenewstack.io/webassembly-sandboxing-ai-agents/

Exactly what I'm building 👇 https://tangled.org/metaend.eth.xyz/wasmbox-cli

#wasm #wasmbox #ai #aisec

love when a platform’s core feature is 'let random AI agents run arbitrary code on your devices' and the founder is like 'hey we never said it had to be *good* code' 🤷‍♂️ #OpenClaw #AIsec #JustAgentThings

It will unify finding the bugs, fixing the bugs, testing the bugs, exploiting the bugs, writing the bugs in the first place, slipping the bug into a competitor CI/CD wait am I still talking out loud?

https://www.securityweek.com/aistrike-raises-7-million-in-seed-funding/

#aisec

#OWASP #Ottawa would like to acknowledge the gracious support from Software Secured for our January Meetup. Their support for the Ottawa Security community through our chapter brings helps us all to skill up.

www.softwaresecured.com

#AppSec #infosec #aisec

⚠️ Most breaches don’t require genius — just opportunity.

Attackers don’t need zero-days. They exploit what’s already exposed:
• Default creds still active
• Config drift no one monitors
• Cloud misconfigs after updates
• APIs exposed by accident

We’re building autonomous agents to close those gaps 24/7 at HACKTIVATE LABS.

The Reality:
Most orgs don’t need more security staff —
they need faster decision loops.
Executed by agents that never sleep.

What we’re testing now:
🧠 AI agents that shape the threat surface in real time
🛰️ Pre-attack recon using live intel feeds
⚔️ Automated red team prep using CVE correlation
🔄 Defense loops that execute without human approval

The goal isn’t alerts.
The goal is autonomous containment.

💬 If you’re building in #AIsec, #Cybersecurity, or #DevSecOps — let’s align.
Tag your team or @mention someone who should see this.

#Automation #RedTeam #AISecurity #SOC #NetOps #SecurityFuture #AIagents

The Reality:
Most orgs think they need a bigger security team.
What they actually need is faster decision loops—
executed by autonomous agents that never sleep.

What we’re proving at HACKTIVATE LABS:
⚙️ 60% of defensive tasks can be automated
📉 False positives can be reduced without blind filtering
🧠 AI can triage alerts with context, not keywords
🚀 Red team prep can start before the first meeting

Security shouldn’t wait for humans.
It should deploy itself.

If you agree — boost this or @mention someone building in #AIsec or #Cybersecurity.
Let’s push the edge forward — together.

#DevSecOps #SecurityAutomation #RedTeamOps #CISO #AIInnovations

RE: https://infosec.exchange/@Hacktivate/115582254829761849

⚠️ Most breaches don’t require genius — just opportunity.

Here’s what attackers actually exploit:
• Default creds still active
• Config drift no one monitors
• Cloud misconfigs after updates
• APIs exposed by accident

We’re building autonomous agents to close those gaps 24/7.

If you’re in #Cybersecurity #AIsec or #DevSecOps — let’s talk.
Tag a team that needs this operational.

#Automation #RedTeam #AISecurity #SOC #NetOps

⚠️ Most breaches don’t require genius — just opportunity.

Here’s what attackers actually exploit:
• Default creds still active
• Config drift no one monitors
• Cloud misconfigs after updates
• APIs exposed by accident

We’re building autonomous agents to close those gaps 24/7.

If you’re in #Cybersecurity #AIsec or #DevSecOps — let’s talk.
Tag a team that needs this operational.

#Automation #RedTeam #AISecurity #SOC #NetOps

🧠 AI + Security Automation — What do you want first?

Which agent should I open-source next?

🔘 Prompt injection defender
🔘 CVE → exploit correlator
🔘 Smart contract auditor
🔘 Recon bot for OSINT / endpoints

Vote, @mention, or drop your own idea.
I’ll build what the ecosystem needs.

#AIsec #Cybersecurity #Automation #Builders

RE: https://infosec.exchange/@Hacktivate/115581917628259124

⚡ 3 Fast Checks Every Network Should Run Today

1️⃣ Unknown devices on VLANs?
2️⃣ Unused open ports pre-attack?
3️⃣ Default creds still active anywhere?

You don’t need a full audit — just a disciplined recon loop.

AI + automation makes this continuous.

#Cybersecurity #AIsec #NetOps #DevSecOps
Want micro playbooks or scripts? @mention me.

🛰️ HACKTIVATE LABS // Current Ops

Actively building:
🔹 AI ReconX – adversarial AI + prompt security scanner
🔹 NetMapper – network discovery & visual intel
🔹 RedOrch – automated red team ops & reporting
🔹 LoRaMonitor – secure LoRaWAN mesh analytics

Testing fusion models: AI + Offensive Security.
If you’re building in #AIsec, #redteam, #DeFiSecurity, @mention me — let’s align signals.

More drops coming. Stay operational. ⚔️

RE: https://infosec.exchange/@Hacktivate/115581912020238418

🛰️ HACKTIVATE LABS // Current Ops

Actively building:
🔹 AI ReconX – adversarial AI + prompt security scanner
🔹 NetMapper – network discovery & visual intel
🔹 RedOrch – automated red team ops & reporting
🔹 LoRaMonitor – secure LoRaWAN mesh analytics

Testing fusion models: AI + Offensive Security.
If you’re building in #AIsec, #redteam, #DeFiSecurity, @mention me — let’s align signals.

More drops coming. Stay operational. ⚔️

#Agentic #AI and #MCP servers are all the rage right now. Vendors are racing to add MCP servers to their stacks and reassure their customers that they are secure. Okay, but are they safe to use? Our latest blog digs in. #cybersecurity #security #aisec https://ironcorelabs.com/blog/2025/mcp-servers-are-electric/

I'm looking forward to attending this one. Added some new exploit demos showing how #MCP servers can go wrong, too. #ai #aisec
https://infosec.exchange/@ironcore/115418574913199184

The lineup of talks and speakers at this year's #LASCon in #Austin looks fantastic. Our own @zmre will be there talking on Friday on the Hidden Risks of Integrating AI. Drop in and say hello! #aisec https://lascon.org/schedule/

Our #defcon 33 talk is now available: Exploiting Shadow Data in AI Models and Embeddings (demos included). Enjoy! #aisec #security https://www.youtube.com/watch?v=O7BI4jfEFwA

You had a good run, pentesters...
So apparently, @xbow — an AI — claims it topped @hackerone No burnout. No caffeine. No Twitter rants about payload encoding. Just pure, scalable exploitation.
It doesn’t even need a hoodie.
While you’re debugging payloads in staging, it’s farming triage points in prod like it’s Doom on God Mode.
Even if it's only half true… what are you doing with your career?
Maybe it's time to pivot. Maybe start offering “human context review” as a service?
We used to joke about Clippy becoming self-aware. Now Clippy does lateral movement and submits reports while you sleep.
#infosec #bugbounty #AIsec #pentest https://xbow.com/blog/top-1-how-xbow-did-it/

Spoke with a client who believes that AI will catch half of all computer security breaches in the future. That's wasteful. Here's why:
A mature solution should not just trap the breach, but it should also generate the appropriate use case so automation will catch any recurrences. That's what a CMMi level 3 organization will do; AI shouldn't regress the organization.
AI will catch about 5 percent of all security breaches. 95 percent will be caught by less resource-intensive technologies.
#aisec

Listening to a book on #AI and they just said something to the tune of

Just as malware and spam have been reduced to merely occasional incidents, in the future, subversion of #AI will be rare.

Almost spat out my drink.

#aisec #fuckaroundandfindout #nothowthisworks