Loading story…
Cloudflare has introduced agent tracing as the first component of its new Cloudflare Agents platform, giving developers deeper visibility into AI agents running on Workers. The feature extends beyond infrastructure-level telemetry by adding spans for agent invocations, model calls, tool execution, approvals, and subagent activity, and it also supports session replay of recorded conversations, tool calls, and results.
Cloudflare said the capability is intended to help teams observe and debug agent behavior, but early coverage highlighted several operational caveats. Reported limitations include inconsistent default payload-recording behavior between Think and Flue, truncation that can make replay non-lossless, and pricing tied to total observability events rather than only the events surfaced in the Agents dashboard. The company said tracing is free during beta and will transition to Workers Observability pricing on October 1, 2026.
Track how attackers are adapting to this technology.
2 events from the most recent confirmed update back to the earliest known activity.
Cloudflare announced Cloudflare Agents, a platform for building and running AI agents on Workers. The later agent tracing release is described as the first component of this broader offering.
Cloudflare launched agent tracing as the first component of Cloudflare Agents to provide visibility into AI agent behavior beyond infrastructure-level tracing. The feature adds spans for agent invocations, model calls, tool execution, approvals, subagent activity, and session replay of recorded conversations and tool activity.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
2 references tracked. Mallory keeps watching after this page renders.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Cloudflare has open sourced **Cloudflare OS**, an internal platform built to control, isolate, and audit how AI agents access sensitive data and external tools. The system uses capability-based access controls and **Gatekeeper** services that hold credentials on an agent’s behalf, allowing policies to be enforced without exposing secrets directly to agent code. Cloudflare said the platform was designed to address security gaps in agent frameworks by limiting what agents can reach and by making their actions attributable and reviewable. A central feature is an observation log that records every resource an agent reads and uses that history to re-check whether downstream actions should still be allowed, extending beyond tool-permission models such as **Model Context Protocol**. Cloudflare said agent execution is isolated through **Dynamic Workers**, sandboxed browser frames, **Durable Object Facets**, and SQLite-backed application state, while model traffic is routed through **Cloudflare AI Gateway** for attribution, rate limiting, and budget controls. The company said Cloudflare OS is being released as open source before a broader managed product launch, with dashboard, development container, and Slack-integrated workspace features still in development.
Aug 23, 2026
AWS introduced **AWS DevOps Agent**, an AI-powered operations assistant designed to help DevOps and SRE teams investigate **AWS Network Firewall** connectivity incidents by analyzing telemetry and configuration data across AWS environments. The agent uses AWS APIs to review firewall logs, **VPC Flow Logs**, route tables, firewall policies, and recent **AWS CloudTrail** activity to identify likely root causes and recommend mitigations, aiming to speed diagnosis of outages and misconfigurations. AWS highlighted several troubleshooting scenarios, including blocked traffic caused by a domain deny list, packet drops tied to stateless rule priority conflicts, and asymmetric routing across Availability Zones. The service can also correlate incidents with recent infrastructure or application changes by integrating with repositories and CI/CD platforms such as **GitHub**, **GitLab Self-Managed**, **AWS CloudFormation**, **AWS CDK**, **Amazon ECR**, and **Terraform**, while alerting workflows can be tied into **Amazon CloudWatch**, **Amazon SNS**, **AWS Lambda**, and **AWS Secrets Manager** to support automated investigation and stronger deployment guardrails.
Jul 27, 2026
Anthropic published research showing that reasoning models do not always reveal their full internal deliberations in their visible chain-of-thought, and separately described Claude’s **“J-space”** as a compact internal workspace tied to deliberate multi-step reasoning. Using a technique referred to as **J-lens**, the company said it can approximate token-level concepts active inside that workspace before the model produces output or takes actions, offering a view into internal representations that are normally hidden from users and defenders. Security practitioners said the finding could create a new layer of AI-agent telemetry beyond outputs and action logs, because internal concepts such as **“ERROR,” “injection,” “fake,” “fictional,” “manipulation,”** and **“fraud”** reportedly appeared in Claude’s workspace before harmful or deceptive behavior became externally visible. The reporting argues that such visibility could support earlier detection, interruption of multi-step agent workflows, staging-time screening, and post-incident forensics, but notes that this telemetry remains controlled by Anthropic rather than exposed to enterprise customers running agents in production.
Jul 14, 2026