←
OX Security271 posts
OX Security avatar

OX Security

@OX__Security

Securing your applications from Prompt to Runtime.

◷ Joined June 2024▧ 167 Photos and videos
OX Security avatar
OX Security@OX__Security·Jul 28

🚨 AI changed how software gets built. Security is still playing catch-up. Agents now write code, connect to tools, provision infrastructure, and execute workflows in real time—while AppSec and CNAPP remain built for a human-led world. OX Security is the first prompt-to-runtime platform built to secure the full agentic development lifecycle, defining the emerging AINAPP category. The Mythos Age needs a new security model. OX built it. ➡️ ox.security/blog/ox-security… -- #AINAPP #AISecurity #CyberSecurity

OX Security avatar
OX Security@OX__Security·5h

🚨 BREAKING NEWS: OX Radar is LIVE! 🌍 🔗 ox.security/blog/introducing… Compromised packages. Malicious dependencies. Exploited CVEs. OX Radar tells you what matters most: Are we affected? Our global correspondents have the scoop. Roll the tape! 🎙️👇

1:06
OX Security avatar
OX Security@OX__Security·7h

🚨 Java4Shell sounds terrifying. The reality is more complicated. CVE-2026-114938 can crash vulnerable Java apps and, under specific conditions, lead to unauthenticated RCE. 📊 FULL REPORT: ox.security/blog/java4shell-… OX Research estimates <0.12% of JVMs are realistically exposed to RCE. Patch now — but prioritize based on actual exposure. #CyberSecurity #Java #CVE

Moshe Siman Tov Bustan avatar
⟳ OX Security retweeted
Moshe Siman Tov Bustan@MosheTov·Nov 17

🚨 agent-framework 1.26.1 - infected with malicious infostealer 🚨 Python package wheel file contains infostealer logic More details soon

OX Security avatar
OX Security@OX__Security·Nov 5

🚨 OpenSSH Flaw Turns Invalid Passwords Into Valid Logins CVE-2026-123158 (CVSS 8.1) can allow password authentication bypass on affected Linux systems. 📊 FULL REPORT: ox.security/blog/openssh-aut… No valid password required. Patch to OpenSSH 10.6p2+ or disable password authentication until updated. #CyberSecurity #OpenSSH #CVE

OX Security avatar
OX Security@OX__Security·Nov 4

Final stop on Moshe’s fall tour: San Francisco 🎸 OX's @MosheTov is taking the stage at @owasp's Global AppSec USA with: 𝐌𝐨𝐝𝐞𝐥 𝐂𝐨𝐧𝐭𝐞𝐱𝐭 𝐏𝐨𝐢𝐧𝐭𝐬 𝐨𝐟 𝐅𝐚𝐢𝐥𝐮𝐫𝐞: 𝐌𝐂𝐏 𝐒𝐞𝐜𝐮𝐫𝐢𝐭𝐲 𝐌𝐞𝐞𝐭𝐬 𝐒𝐜𝐚𝐥𝐞 📅 November 5 ⏰ 1:15 PM PT 📍 San Francisco, CA See you there 🤘 #OWASPSanFran26 #GlobalAppSec26

OX Security avatar
OX Security@OX__Security·Oct 30

🚨 Malicious Claude Code extension plants a persistent SSH backdoor. A tampered Anthropic.claude-code v2.1.313 was distributed through Cursor’s marketplace. 📊 FULL REPORT: ox.security/blog/malicious-c… It adds an attacker SSH key, installs persistence, and can survive extension removal. If you installed it: treat the host as compromised, remove persistence, update, and rotate creds. #CyberSecurity #SupplyChainSecurity #ClaudeCode

OX Security avatar
OX Security@OX__Security·Oct 29

Next stop on Moshe’s fall tour: San Francisco. 🎸 @MosheTov is taking the stage at @RBLN26 with: 𝐌𝐨 𝐕𝐮𝐥𝐧𝐬 𝐌𝐨 𝐏𝐫𝐨𝐛𝐥𝐞𝐦𝐬: 𝐑𝐞𝐬𝐩𝐨𝐧𝐬𝐢𝐛𝐥𝐞 𝐃𝐢𝐬𝐜𝐥𝐨𝐬𝐮𝐫𝐞 & 𝐈𝐫𝐫𝐞𝐬𝐩𝐨𝐧𝐬𝐢𝐛𝐥𝐞 𝐌𝐚𝐢𝐧𝐭𝐚𝐢𝐧𝐞𝐫𝐬 𝐢𝐧 𝐭𝐡𝐞 𝐀𝐈 𝐄𝐫𝐚 📅 November 4 ⏰ 1:30 PM PT 📍 San Francisco, CA See you there 🤘 #Cybersecurity #ResponsibleDisclosure #OpenSourceSecurity #VulnerabilityResearch

OX Security avatar
OX Security@OX__Security·Oct 28

Knowing which AI agents you have is no longer enough. The real question is: What are they actually doing? 🚀 Today we're introducing Agent Activity, now in early access as part of OX VibeSec and OX Cloud ➡️ Read more: ox.security/blog/introducing… Agent Activity gives security teams step-by-step visibility into agent behavior at runtime, and the controls to act on it 👇 → Trace every step: prompts, responses, MCP calls, tool usage, and read/write access → See when agents touch PII, secrets, tokens, or financial data → Build custom guardrails by model, MCP server, and skill, then flag or block violations → Start with 100+ built-in policies, with more on the way → Get coverage from endpoint to production across OX VibeSec and OX Cloud, plus a new LiteLLM connector Agents move faster than static scans. Securing them means understanding and controlling what they do while they run. #AISecurity #Cloud #AgenticAI #RuntimeSecurity