https://cybertoolchain.io/tools/ox-security New releases and features in OX Security, tracked by The Cyber Toolchain. en Wed, 28 Oct 2026 16:05:40 GMT https://www.ox.security/blog/introducing-agent-activity-see-what-your-ai-agents-are-actually-doing/ https://www.ox.security/blog/introducing-agent-activity-see-what-your-ai-agents-are-actually-doing/ Wed, 28 Oct 2026 16:05:40 GMT OX Security adds Agent Activity, a runtime tracing and guardrail feature for AI agents now in early access across OX.VibeSec and OX.Cloud⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds a LiteLLM connector to bring LLM proxy traffic into OX Security's agent visibility picture.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • OX Security now traces each AI agent session step by step — covering prompts and responses, MCP server and tool calls, read/write access permissions, and sensitive data touches — via the new Agent Activity feature in early access on OX.VibeSec and OX.Cloud. • Build custom runtime guardrails scoped to specific AI models, MCP servers, and skills, with a choice to flag or block violations at a severity you set. • Start agent governance from 100+ built-in out-of-the-box security policies covering runtime agent behavior. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ox-security https://www.ox.security/blog/litellm-1-107-0-compromised-with-a-rat-infostealer/ https://www.ox.security/blog/litellm-1-107-0-compromised-with-a-rat-infostealer/ Wed, 21 Oct 2026 15:32:36 GMT OX Security detects and blocks malicious LiteLLM 1.107.0 (RAT + infostealer) via VibeSec pipeline scanning⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds `litellm 1.107.0` to the OX Security malware database, blocking installation for VibeSec customers and redirecting them to the safe version `1.106.0`.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • OX platform pipeline scan now blocks code pushes that include the compromised `litellm 1.107.0` as a dependency. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ox-security https://www.ox.security/blog/ox-security-launches-ox-cloud-ai-agent-security/ https://www.ox.security/blog/ox-security-launches-ox-cloud-ai-agent-security/ Wed, 16 Sep 2026 11:05:00 GMT OX Security launches OX Cloud with AI Detection and Response (AIDR) and Agentic Attack Surface Management (AASM) for AI-agent visibility in cloud environments.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds AI Detection and Response (AIDR) to detect and govern AI agent activity across cloud and runtime environments in real time.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds Agentic Attack Surface Management (AASM) to discover AI agents, models, MCP servers and non-human identities and map what they can reach. • Introduces OX Cloud as a full CNAPP platform covering Cloud Security Posture Management (CSPM), Kubernetes Security Posture Management (KSPM), Data Security Posture Management (DSPM), runtime vulnerability detection, cloud inventory and graph-based attack path analysis. • Provides reachability-based prioritization to filter out risks that cannot actually be reached in cloud environments. • Alert detail views show who or what acted, what they touched and what else they could have reached. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ox-security https://www.ox.security/blog/ox-cloud-cnapp-coverage-plus-runtime-security-for-ai-agents/ https://www.ox.security/blog/ox-cloud-cnapp-coverage-plus-runtime-security-for-ai-agents/ Wed, 16 Sep 2026 10:37:56 GMT OX Cloud launches as a unified CNAPP platform with real-time AI agent detection (AIDR), runtime inspection, and reachability-based prioritization.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds AIDR (AI Detection and Response) for real-time detection and governance of AI-driven usage, configuration, and threats across cloud and runtime environments, including AI agents calling tools, models accessing data, and MCP servers executing autonomously.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds Agentic Attack Surface capability, powered by the OX Agent, to uncover hidden backdoors and reachable exposures through agentic-level inspection. • Adds Runtime Events capability for investigating runtime anomalies with full context to accelerate incident detection and triage. • Adds Runtime Vulnerabilities detection to identify vulnerabilities actively exposed in running workloads and prioritize what is truly exploitable. • Adds Cloud Graph and Attack Path Mapping to visualize relationships across cloud assets, including lateral movement paths and blast radius. • Adds Cloud Inventory providing a continuously updated inventory of every workload, identity, data store, Kubernetes cluster, and AI agent actually running in the environment, including shadow AI and unmanaged non-human identities. • Adds CSPM (Cloud Security Posture Management) for continuous detection of cloud misconfigurations and compliance enforcement across all cloud accounts. • Adds KSPM (Kubernetes Security Posture Management) for monitoring Kubernetes security risks including misconfigurations and policy compliance. • Adds DSPM (Data Security Posture Management) to discover, classify, and protect sensitive data across cloud environments. • Introduces reachability-based filtering to eliminate unreachable misconfigurations, vulnerable packages, and supply-chain exposures from the findings backlog, surfacing only what is exploitable and evidenced. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ox-security https://www.ox.security/blog/vet-every-dependency-your-agents-install-with-ox-vibesec/ https://www.ox.security/blog/vet-every-dependency-your-agents-install-with-ox-vibesec/ Wed, 09 Sep 2026 03:00:00 GMT OX VibeSec adds Dependency Vetting to block malicious or freshly published packages before AI agents install them. • Adds Dependency Vetting capability that inspects every AI agent install attempt against policy and blocks known-malicious packages outright before they touch the developer machine or SBOM. • Introduces a configurable cool-down period that blocks freshly published packages until the community has had time to flag them. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ox-security