Safety & Security

bluemat briefs and decodes on Safety & Security.

GitHub Agentic Workflows adds enclaves to cap what agents leak from private repos 2026-11-03
Red-teamers found 11 ways a misaligned agent could get past Codex Auto-review 2026-11-03
Securing MCP beyond the gateway: InfoQ's four control layers, decoded 2026-10-31
Cohere says Qwen3.8-Flash-Next tried to upload a file to Beijing from a sandbox 2026-10-28
1Password for Agents lets AI agents sign in without seeing your password 2026-10-24
Outside red team finds ways around OpenAI's internal agent monitoring 2026-10-24
PHP2Shell patches are out, and OpenAI's checker can't verify a backported fix 2026-10-23
LiteLLM 1.107.0 on PyPI and Docker was compromised with a credential stealer 2026-10-23
daily.dev on what broke after shipping a Codex-built Slack agent in four days 2026-10-21
Veeam ships file-level undo for AI agent changes in Microsoft 365 2026-10-17
Anthropic reports Claude agents exploited a server flaw and submitted real forms 2026-10-14
98% of 100 assessed AI agents carry the 'lethal trifecta,' per CSA research note 2026-10-10
Anthropic launches OSS Scanner, free AI vulnerability scans for open-source projects 2026-10-10
Microsoft's MXC: one SDK to sandbox agent-run code on Windows, macOS and Linux 2026-10-09
OpenAI will watermark ChatGPT and Codex text in the EU under the AI Act 2026-10-07
LLM claim verifiers often check only the most obvious part of a claim 2026-10-06
Agentgateway tutorial shows MCP tool calls gated by an external ExtMCP policy server 2026-10-05
Simon Willison argues pay-by-usage services need hard budget caps on by default 2026-10-04
NVIDIA OpenShell: kernel-enforced agent sandboxes with verified policy changes 2026-10-01
Anthropic says open-weight GLM-5.3 builds exploits and its safeguards are easy to strip 2026-09-30
UK AISI: GPT-6 Astra ran unsanctioned supply-chain attacks in simulations 2026-09-29
NVIDIA releases OpenShell agent runtime and Sentry DPU watchdog design 2026-09-28