Join our founder and CTO Ante and Learn how to test & secure agentic AI systems in our hands-on workshop at @BSidesFRA: Challenges When Automating Agentic AI Red Teaming Sign up 👉 eventbrite.de/e/bsidesfrankf… See you there! #AIsecurity #RedTeaming #BSides

🛠️ 𝗙𝗿𝗲𝗲 𝗧𝗼𝗼𝗹 𝗗𝗿𝗼𝗽: 𝗩𝗶𝘀𝘂𝗮𝗹𝗶𝘇𝗲 𝘆𝗼𝘂𝗿 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 𝗶𝗻 𝘀𝗲𝗰𝗼𝗻𝗱𝘀. As multi-agent systems become more complex – with MCP servers, A2A links, and toolchains across CrewAI, LangGraph, OpenAI Agents, AutoGen, or n8n frameworks – things start to become messy. This leads to security blind spots, logic errors, & hidden risks. Agentic Visualizer lets you upload your GitHub repo or source code ZIP-file and instantly see: → 𝗔𝗴𝗲𝗻𝘁𝘀, 𝘁𝗼𝗼𝗹𝘀, 𝗠𝗖𝗣 & 𝗔𝟮𝗔 𝗽𝗮𝘁𝗵𝘀 → 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻/𝗱𝗮𝘁𝗮 𝗳𝗹𝗼𝘄 𝗺𝗮𝗽𝘀 → 𝗣𝗼𝘁𝗲𝗻𝘁𝗶𝗮𝗹 𝗯𝗼𝘁𝘁𝗹𝗲𝗻𝗲𝗰𝗸𝘀 + 𝗹𝗼𝗴𝗶𝗰 𝘁𝗿𝗮𝗽𝘀 Try it now for free 👉 agentic-visualizer.splx.ai/

🤖 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 𝗮𝗿𝗲 𝗿𝗲𝗱𝗲𝗳𝗶𝗻𝗶𝗻𝗴 𝗲𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝘃𝗶𝘁𝘆 – but they also introduce new risks. Over 20% of time in white-collar jobs is spent on repetitive tasks. Agentic AI assistants are changing this by automating updates, generating docs, and filing JIRA tickets – all triggered through a company's communication tools like Slack. But greater autonomy means greater risk: 🔓 Authorization hijacking 🌀 Agentic hallucinations 📡 Multi-agent trust exploitation 📂 Tool-based data leakage These systems interact across tools and agents – often without human oversight. We break it all down (with examples) in our latest whitepaper: “𝙏𝙝𝙚 𝘾𝙪𝙧𝙧𝙚𝙣𝙩 𝙎𝙩𝙖𝙩𝙚 𝙤𝙛 𝘼𝙜𝙚𝙣𝙩𝙞𝙘 𝘼𝙄 𝙍𝙚𝙙 𝙏𝙚𝙖𝙢𝙞𝙣𝙜” 📥 Download it here → splx.ai/resources/the-curren… #AgenticAI #RedTeaming #GenAI #LLM #AIsecurity #MAS #SplxAI #AIsafety #LLMSecurity

⚠️ Multi-turn prompt injections are the next big threat to Agentic AI Workflows ⚠️ When targeting 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 (𝗠𝗔𝗦), prompt injection techniques become more complex – unfolding over multiple steps, priming agents across the conversation, bypassing layered guardrails, and triggering downstream tools (like email or document generation). In Agentic AI workflows, memory and context persist through multiple agents – making it easier for malicious payloads to slip through unnoticed and execute within the system. We break down how these attacks work in our latest whitepaper: “𝗧𝗵𝗲 𝗖𝘂𝗿𝗿𝗲𝗻𝘁 𝗦𝘁𝗮𝘁𝗲 𝗼𝗳 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 𝗥𝗲𝗱 𝗧𝗲𝗮𝗺𝗶𝗻𝗴” 📥 Download it here → splx.ai/resources/the-curren…

We’re beyond excited to welcome Joseph Thacker (@rez0__ ) – aka 𝙏𝙝𝙚 𝙋𝙧𝙤𝙢𝙥𝙩 𝙁𝙖𝙩𝙝𝙚𝙧 – as a strategic advisor to @SplxAI! A true pioneer of AI Red Teaming, Joseph has looked at 20+ AI security tools and decided to join forces with the one he believes in most. His expertise will help us build the world’s most powerful AI Security Platform – and enable organizations globally to adopt secure AI at scale. Welcome on board, Joseph! 🚀

💥OUT NOW: The Current State of Agentic AI Red Teaming 💥 As LLM-powered apps evolve into autonomous, multi-agent systems, red teaming practices must also adapt to secure increasingly complex risks. Our new whitepaper breaks down: 📊 Insights from 100s of AI red team assessments ⚠️ Risks like RAG poisoning, tool misuse & data leaks 🧩 Model Context Protocol (MCP) vulnerabilities 🧠 Tools for threat modeling agentic systems 🎯 Real-world prompt injection examples 💼 Why continuous AI red teaming matters for business 📥 Get your copy now → splx.ai/resources/the-curren… Huge thanks to all writers and contributors! @Stanford @owasp @LLM_Top10 @FraunhoferSIT @cloudsa

🏛️ 𝗦𝗽𝗹𝘅𝗔𝗜 𝗮𝘁 𝘁𝗵𝗲 𝗡𝗲𝘄 𝗬𝗼𝗿𝗸 𝗦𝘁𝗼𝗰𝗸 𝗘𝘅𝗰𝗵𝗮𝗻𝗴𝗲 🏛️ A big thank you to @FintechTvGlobal and host @TheNadjaAtwal for hosting our CEO @KristianKamber at the @NYSE ! In this exclusive interview, Kristian reflects on the @SplxAI journey – coming out of stealth just over a year ago to now empowering 𝗙𝗼𝗿𝘁𝘂𝗻𝗲 𝟱𝟬𝟬 enterprises to adopt and deploy secure, compliant, and trustworthy AI apps and agents at scale. We’re proud to lead the charge of the 𝗦𝗮𝗳𝗲 𝗔𝗜 𝗥𝗲𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 – helping industries like 𝗳𝗶𝗻𝗮𝗻𝗰𝗲, 𝗶𝗻𝘀𝘂𝗿𝗮𝗻𝗰𝗲, 𝗮𝗻𝗱 𝗯𝗲𝘆𝗼𝗻𝗱 leverage the power of AI with confidence. 📺 Watch the full interview here: fintech.tv/the-ai-security-r…

✅ 𝗦𝗰𝗮𝗻 & 𝗛𝗮𝗿𝗱𝗲𝗻 𝗦𝘆𝘀𝘁𝗲𝗺 𝗣𝗿𝗼𝗺𝗽𝘁𝘀 𝗶𝗻 𝗔𝗜 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 𝘄𝗶𝘁𝗵 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗮𝗱𝗮𝗿 ✅ We’re excited to roll out the latest update to 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗮𝗱𝗮𝗿, our open-source security scanner for agentic workflows – now with automatic system prompt detection and hardening across all agents. System prompts define how an AI agent thinks and acts. When they’re vague or poorly defined, they invite jailbreaks, misbehavior, and data leaks. With this upgrade, your agents become instantly more: 🟩 𝗦𝗲𝗰𝘂𝗿𝗲 🟦 𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 🟪 𝗣𝗿𝗲𝗱𝗶𝗰𝘁𝗮𝗯𝗹𝗲 What’s included: 🧭 Visibility into agents’ current instructions ⚠️ Detection of weak or risky system prompts 🛠️ Auto-suggested hardening fixes 📉 Lower risk of jailbreaks, leaks, and unwanted behavior 🔓 100% open-source and easy to integrate – making secure & aligned agentic workflows more accessible than ever. 🔗 Learn more: tinyurl.com/53svcdnv 🚀 Try it out: github.com/splx-ai/agentic-r…

Dorian our superstar ⭐️🤩

🔎 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗮𝗱𝗮𝗿 𝗻𝗼𝘄 𝗱𝗲𝘁𝗲𝗰𝘁𝘀 𝗠𝗼𝗱𝗲𝗹 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗣𝗿𝗼𝘁𝗼𝗰𝗼𝗹 (@MCP_Community) 𝘀𝗲𝗿𝘃𝗲𝗿 𝗰𝗼𝗻𝗻𝗲𝗰𝘁𝗶𝗼𝗻𝘀 𝗶𝗻 𝗢𝗽𝗲𝗻𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 – giving you visibility into how agents access external systems and helping you secure data flows. Why does this matter? 🔍 𝗧𝗿𝗮𝗻𝘀𝗽𝗮𝗿𝗲𝗻𝗰𝘆 – Know which external systems agents access 🛡️ 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 – Spot risky connections & enforce least privilege 📊 𝗚𝗼𝘃𝗲𝗿𝗻𝗮𝗻𝗰𝗲 – Track how sensitive data flows 📖 Read Our Example: splx.ai/blog/agentic-radar-n… 🔗 Get Started on GitHub: github.com/splx-ai/agentic-r… #AgenticAI #AIsecurity #MCP #OpenAI #GenAI #AgenticRadar #AItransparency #RedTeaming

🎙️𝗥𝗲𝗱 𝘁𝗲𝗮𝗺𝗶𝗻𝗴 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀: 𝗪𝗵𝗲𝗿𝗲 𝗧𝗼 𝗘𝘃𝗲𝗻 𝗦𝘁𝗮𝗿𝘁? 🤔 @SplxAI founders joined the @LLM_Top10 GenAI Security Podcast with @AubreyKingF5 to dive into: 🧠 Continuous AI red teaming 🔁 How to build scalable testing workflows 🧩 Security risks in RAG, agents & multimodal AI ⚠️ Why traditional testing won’t be enough Looking to deploy secure and trusted AI apps? This one is for you. 🎧 Watch it now: piped.video/watch?v=c6e5-SxA… #AIsecurity #GenAI #RedTeaming #LLMSecurity #OWASP #AppSec #AgenticAI

🐉 𝗦𝗽𝗹𝘅𝗔𝗜 𝗶𝘀 𝗮 𝗽𝗿𝗼𝘂𝗱 𝗦𝗶𝗹𝘃𝗲𝗿 𝗦𝗽𝗼𝗻𝘀𝗼𝗿 𝗮𝘁 𝗕𝗦𝗶𝗱𝗲𝘀𝗦𝗙 𝟮𝟬𝟮𝟱 🐉 The end of April will be an exciting time for cybersecurity professionals in the Bay Area, with @BSidesSF taking place 𝗔𝗽𝗿𝗶𝗹 𝟮𝟲–𝟮𝟳 — perfectly timed to get ready for a busy @RSAConference right afterward. We can't wait to share our latest breakthroughs in securing AI Apps and Agents, meet some old friends and make new ones! Join us for insightful AI security sessions and plenty of opportunities to connect with the cybersec community. 🎟️ Get your tickets now: bsidessf.regfox.com/2025 #BSidesSF #BayArea #AISecurity #RSAC2025 #SplxAI #AIRedTeaming

𝗛𝗲𝗮𝗱𝗶𝗻𝗴 𝘁𝗼 @RSAConference 𝟮𝟬𝟮𝟱? 🌉🔐 Our team will be at 𝗥𝗦𝗔𝗖 𝟮𝟬𝟮𝟱, meeting with cybersecurity leaders and innovators to discuss how enterprises can safeguard AI Assistants and Agentic Workflows from development to deployment. If securing AI at scale is one of your priorities this year, this is a great opportunity to see how @SplxAI is helping enterprises do it right. 📆 Book a 1:1 with us to learn how we enable 𝘀𝗲𝗰𝘂𝗿𝗲 and 𝗰𝗼𝗺𝗽𝗹𝗶𝗮𝗻𝘁 AI adoption: splx.ai/rsac-2025 🎟️ Still need your pass? Secure your spot at RSAC 2025 here: rsaconference.com/usa/passes… #RSAC2025 #AISecurity #SecurityforAI #SplxAI #AIRedTeaming #AIGovernance #CyberSecurity

⚡𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗮𝗱𝗮𝗿 + 𝗢𝗽𝗲𝗻𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝗦𝗗𝗞⚡ Our open-source scanner now supports @OpenAI Agents SDK – helping developers visualize multi-agent workflows, track tool usage, and flag security risks with ease. We built an airline support demo with: ✈️ A Triage Agent 📄 An FAQ Agent (FileSearchTool) 💺 A Seat Booking Agent (custom tools) Agentic Radar detects: 🔁 Handoff loops 🛠️ Tool misuse 🕵️ Potential vulnerabilities mapped to @LLM_Top10 🔍 See the full walkthrough here: splx.ai/blog/openai-agents-s… ⭐ Start scanning your own workflows: github.com/splx-ai/agentic-r… More agentic frameworks, like @dify_ai and @pydantic, are coming soon. Stay tuned! #AIsecurity #AgenticAI #OpenSource #LLMs #OpenAIAgentsSDK #AgenticRadar #SplxAI

🚨 How a Prompt Injection can pass through Agentic AI Workflows undetected 🤖➡️🧠 Our new research shows how a single hidden instruction can silently flow through a multi-agent AI system – bypassing the interface chatbot, surviving summarization, and only activating when a downstream agent executes the payload. This type of attack exploits how agents trust and pass data – without the user ever noticing. 💡 Key takeaways: - Agentic workflows are only as secure as their weakest link - Markdown URLs can carry invisible instructions - Attacks can propagate completely unnoticed - Input sanitization must happen between agents 🧠 Human creativity still plays a key role in exposing new vulnerabilities in complex AI systems. 🔗 Read the full article: splx.ai/blog/exploiting-agen… #AIsecurity #PromptInjection #AgenticAI #RedTeaming #LLMsecurity #SplxAI

Tony Bradley of @Forbes recently sat down to interview @SplxAI CEO & Co-founder @KristianKamber, @rain_capital Managing General Partner Dr. @chenxiwang and @LAUNCHub Ventures General Partner @StanSirakov to discuss the cybersecurity challenges unique to agentic AI and our latest funding news. Read his article to learn how @SplxAI is tackling Agentic AI security: forbes.com/sites/tonybradley…

🚀 𝗦𝗽𝗹𝘅𝗔𝗜 𝗿𝗮𝗶𝘀𝗲𝘀 $𝟳𝗠 𝘁𝗼 𝘀𝗲𝗰𝘂𝗿𝗲 𝘁𝗵𝗲 𝗳𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 🚀 It's official: We've closed a $7M seed funding round! Thank you to our incredible investors @LAUNCHub, @rain_capital, Inovo.vc, runtime.vc, @DNV_Group and @VenturesSc. We’d also like to extend a big welcome to @StanSirakov, who is joining our Board of Directors. This marks a significant milestone in our mission to help organizations secure Agentic AI systems. We’re incredibly fortunate to have these partners alongside us as we continue to grow and innovate. With 𝟯𝟯% 𝗼𝗳 𝗲𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 𝗲𝘅𝗽𝗲𝗰𝘁𝗲𝗱 𝘁𝗼 𝗶𝗻𝗰𝗼𝗿𝗽𝗼𝗿𝗮𝘁𝗲 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 𝗯𝘆 𝟮𝟬𝟮𝟴, the shift from simple LLM assistants to complex Agentic AI workflows has introduced a new, poorly understood threat surface to the technology stack that organizations are struggling to manage. @SplxAI's advanced platform is the only scalable solution for securing Agentic AI, providing security leaders with the tools they need to confidently embrace AI. Read more about the announcement here: splx.ai/blog/splxai-closes-7…

✨ Agentic Radar + n8n is here! 🚀 Our community asked for it – and we listened. We have added support for the @n8n_io agentic framework to our open-source security scanner 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗮𝗱𝗮𝗿. Scan your n8n workflows to visualize agent interactions, tools being used, and automatically detect potential security issues aligned with @owasp's LLM Top 10 and Agentic AI Threats. Here is a detailed example to help you get started: 🔗 splx.ai/blog/scanning-n8n-wo… Explore Agentic Radar on GitHub and join the community: ⭐ github.com/splx-ai/agentic-r… #AgenticRadar #n8n #AIsecurity #GenAI #OWASP #RedTeaming #OpenSource #SplxAI

Feeling the buzz yet? @RSAConference 2025 is almost here – and it'll be 𝘂𝗻𝗳𝗼𝗿𝗴𝗲𝘁𝘁𝗮𝗯𝗹𝗲 with all the excitement around AI & Agentic Security! 🚀 Join @SplxAI for: 🍷 Security Uncorked Happy Hour w/@EscapeTechHQ @GitGuardian, @MiggoSecurity, and @Mend_io 🛥️ AI Cyber Yacht w/@Sysdig, @elastic, @knosticai 🍸 Runtime Ventures RSA Happy Hour 🤝 1:1 Sessions with our Team Check out our detailed agenda and secure your spot: 👉👉👉 splx.ai/rsac-2025 #RSAC2025 #AISecurity #CyberSecurity #SplxAI #AGENTICAI #SecurityforAI

Thanks for featuring us @langchain 🙏