non sono forte da 2 anni e mezzo ? fra 2 anni fa stavo dentro gli sf tu manco cosai chi sono se va bene

ai pqp eu sem entender nada achei q tava qisse a emam cosai

Indipendentemente da tutto,ogni accade la stessa cosaI fan vengono mantenuto e considerati oro fin quando hanno bisogno.Poi una volta usciti il rispetto per le persone che li hanno seguiti diviene 0.Davanti una situazione del genere chi vi ha seguito meriti una spiegazione #gfvip

As Anthropic Mythos drove a fresh wave of headlines this week—highlighting both its advanced capabilities and how easily such systems could be misused—I made my way to a conference room just outside Washington, D.C. There, a cross-sector group of AI security practitioners, standards-setters, and policy experts had gathered to figure out what securing AI should actually look like. Outside the industry, their acronyms—SANS, NIST, CoSAI, OWASP—may not mean much. Inside security, they help set the rules organizations around the world follow. But right now, those rules are struggling to keep up. I had been invited to sit in on the discussion as organizations race to plug AI into everything—handing over sensitive data and critical workflows—even as those same systems are becoming more attractive targets for adversaries. ⬇️

La Coalition for Secure AI (CoSAI) publicado un marco técnico para gestionar la identidad de los agentes de IA autónomos. El problema: los sistemas actuales de gestión de accesos fueron diseñados para personas, no para software que actúa solo. ▶️derechodelared.com/2026/04/2…

Il mio voto è pari a ZERO...E per dirti cosai comunica questa foto...🤔🤔🤔👇👇👇

The Coalition for Secure AI (#CoSAI) has released a new Agentic IAM framework to secure enterprise AI agents with verifiable identities and traceable delegation chains. The paper offers practical guidance for establishing secure AI access controls on existing infrastructure.

It's great to welcome @zenitysec to the #CoSAI community! We look forward to your contributions as we work together to shape the standards for secure AI development.

The standards for AI agent security are being written right now. Zenity has joined #CoSAI to help shape the frameworks enterprises will rely on to govern agentic systems. 🤝 If you are deploying agents, this is not optional. 🙅‍♀️ Read more 👉 eu1.hubs.ly/H0txVV80 #AISecurity #AgenticAI

L'@UQO rejoint une coalition internationale sur la sécurité de l’IA. L'Université annonce son adhésion à la Coalition for Secure AI (CoSAI), une initiative visant à renforcer la sécurité des systèmes d’intelligence artificielle. uqo.ca/nouvelles/174612 @OASISopen #IA

The agentic security gap is real: AI agents are already running incident response, but the infrastructure to do it safely is largely unbuilt. Read the latest from the Coalition for Secure AI (#CoSAI): Blog: coalitionforsecureai.org/whe… Paper: coalitionforsecureai.org/wp-…

Este es el primer zing que tengo y fue un regalo,quedo bien bonito,me gusto :3,muchas HaRi gatos Cosai mas,Bery thankiii us #staryuukizing

We are making one (via @OASISopen CoSAI) for AI - paper to publish in a couple of weeks.

Great work by Coalition for Secure AI (#CoSAI) Sponsor @Hacker0x01 on the launch of their Agentic Prompt Injection Testing! 🎉 Proud to see our members advancing this important work toward a more secure AI ecosystem. Read more in their press release: hackerone.com/press-release/…

I've been saying this in CoSAI and IETF discussions for months: protocol standardization without security architecture is just a shared attack surface. Now we have the proof. Microsoft's own Azure MCP Server had a CVSS 8.8 SSRF that leaks managed identity tokens. The vendor that helped build the protocol couldn't secure its own implementation. Adversa AI found 30 CVEs in the MCP ecosystem in 60 days. 38% of scanned servers have zero authentication. When I review agent architectures, the first thing I check is trust boundary design at the protocol layer. Most teams skip it entirely because "it's a standard." Standards don't ship secure by default. Your architecture decisions do. securityweek.com/microsoft-p…

Me lo chiedo anch’io. Cosa li attrae, cosai li potrà mai spingere a “gustare” quella ciofeca chimica alla fragranza di ano non lavato da giorni, senza aver mai aspirato una sigaretta? Il pensiero che “Eh fa meno male” o “non sa di catrame”? Un nuovo passatempo? Bah.

Read the OASIS press release ➡️ oasis-open.org/2026/02/09/ci… Read the blog post by @santosomar, CoSAI Project Governing Board Co-Chair, @Cisco ➡️ coalitionforsecureai.org/cis… #CoSAI #ProjectCodeGuard #AISecurity #SecureAI #collaboration #AI #OASIS

Major milestone: @Cisco has donated Project CodeGuard to the Coalition for Secure AI (CoSAI), an OASIS Open Project.