Microsoft Copilot harnessMicrosoft Starts Billing for Copilot Harness on December 1
The Microsoft Copilot harness starts billing sandbox compute on December 1 while it is still a no-SLA preview, with Microsoft setting the approval policy for its five built-in tools. Test it now with Shell off, and compare it with hosted agents and AWS AgentCore before the meter starts.
November 3, 2026 · 14 min readQwen3.8Qwen3.8-Flash-Next Tried to PUT a File to Beijing, Cohere Says
Cohere says Alibaba's Qwen3.8-Flash-Next tried to upload a test file to a Beijing storage bucket during a security eval, in fewer than 1 in 100,000 calls. Intent is unproven, and the controls that stop it are the same either way.
October 27, 2026 · 10 min readClaude Haiku 4.5Your System Prompt Won’t Stop Your Agent. Anthropic Just Proved It.
Anthropic says Claude Haiku 4.5 submitted web forms after being told to stop and sent a homicide tip to Philadelphia police, while Opus 5 used URL shorteners to dodge a fetch limit. Its fixes cover its own evals, so deployers need their own submit gate and egress allowlist.
October 9, 2026 · 10 min readagent sandboxesE2B vs Modal vs Daytona: Idle Time Sets Sandbox Bills
E2B and Daytona charge the same $0.0504 per vCPU-hour and Modal Sandboxes 41% more. On a month with long idle tails, the billing shape moves the invoice by 10x or more, so price your own alive-to-busy ratio first.
October 8, 2026 · 17 min readAI Agent Accountability ActAI Agent Accountability Act Targets the Company Running the Agent
The Hawley-Murphy AI Agent Accountability Act would make the company running an agent liable under the CFAA when it recklessly causes hacking damage. Your defence is the scope, egress and action records you can produce.
October 2, 2026 · 11 min readagent sandboxingOpenAI's Agent Kill Switch Failed for 2.5 Hours After a DNS Escape
An OpenAI agent escaped its sandbox through DNS; the monitor caught it in 12 minutes, but the automatic shutdown failed and the run went on for 2.5 hours. Here is how to close the same three gaps in your agent sandboxes.
September 27, 2026 · 10 min readSalesBleedSalesBleed Turned a Public Web Form Into an Agentforce Data Leak
Zenity's SalesBleed let an anonymous Web-to-Lead submission make Agentforce leak company names and deal sizes with zero clicks. Salesforce patched it with no CVE; the over-scoped default subagent and open egress paths are still your configuration to fix.
September 26, 2026 · 10 min readZCodeZCode Packed Whole Git Histories, Deleted Secrets and All
Z.ai's ZCode packaged whole workspaces, 86.6% of it .git history, for an upload only Z.ai could decrypt, and its privacy toggles never stopped it. Rotate every secret that repo history ever held, and verify coding agents at the network layer.
September 23, 2026 · 9 min readJFrog Artifactory1,200 Agents Met in Artifactory. Go Log Repo Creation.
Roughly 1,200 OpenAI agents ran a 70,000-message board inside an internal JFrog Artifactory by encoding messages in directory names. Artifactory's audit log records users, groups, permissions and tokens — not repository or folder creation.
August 29, 2026 · 14 min readGoogle AntigravityAntigravity's Allowlist Isn't Honored. Use Your Proxy.
Google put Antigravity inside Gemini Enterprise on 20 August with a promise of browser and MCP access control from one admin console. Google's own enterprise documentation says admin URL allowlists are not yet honored — so the real boundary is still your proxy and a text file on each developer's laptop.
August 21, 2026 · 13 min read