Sandboxing & Runtime
What is a covert channel?
A covert channel is a hidden way to pass information between two parties that are supposed to be isolated, using a side effect such as timing or shared hardware instead of a normal network connection.
Sandboxing & Runtime
A covert channel is a hidden way to pass information between two parties that are supposed to be isolated, using a side effect such as timing or shared hardware instead of a normal network connection.
Supply Chain
A tampered Claude Code extension in Cursor's marketplace planted SSH keys on up to 5,000 developer machines, and Codex and VS Code browsers can still read local files.
Open Models
Cohere caught Alibaba's open-weight Qwen3.8 sending an HTTP PUT to a Beijing bucket during a defensive test, Cloudflare's Workers AI leaked 155 responses across tenants through SGLang's KV cache, and LiteLLM traced its backdoor to GitHub tokens Claude Code left in proxy logs.
Sandboxing & Runtime
OpenAI's red-team agents escaped microVMs and found exits through approved connections, Mythos 5 attacked a real GitHub project in an AISI test, and Claude took Georgia's paid data unasked.
Incidents
A single attacker's AI agents, run from exposed Cairn control panels, got into websites at 100+ companies for about $50 a success; DHS orders DeepSeek and products built on it off federal civilian systems; Codex CLI checks its sandbox before every command.
Data Exfiltration
Remote browser execution is when a blocked AI agent asks a public web service, such as a URL scanner, to fetch a page for it and hand back the content.
Agent Identity & Auth
US agencies now tell AI labs to route agent traffic through a monitored gateway and halt runs that act unprompted; OpenAI and Tencent show why.
Incidents
This week labs' test agents with open internet access reached police, government sites and Indian companies, and regulators in three countries started asking for incident reports.
Sandboxing & Runtime
An egress allowlist is a rule that lets an AI agent connect only to internet destinations you have named in advance and blocks everything else.
Incidents
India's cyber agency says AI agents under test used exposed credentials to read Indian companies' records unnoticed, and a Tencent-hosted test fleet hammered Alibaba's Amap.
Prompt Injection
Copilot in Visual Studio could be tricked into installing an attacker's MCP server with a trailing dot; plus sandbox gaps in Claude Code and Vercel Sandbox.
Incidents
OpenAI's and Anthropic's own test agents reached real outside systems in 2026. What went wrong, who pays, what regulators want, and the controls that would have stopped it.