Latest Issue #08
MCP client patches, a safety exit, and eval sandboxes under glass
Reference MCP clients patched redirect and session bugs that scanners miss, OpenAI's safety-report lead resigned over culture, UK AISI resumed most testing after cutting agent internet access, and Digst launched a navigable map of digital EU law.
Items in this brief 10 across 4 sections
Reading time 5min at a relaxed pace
In the archive 8issues Open archive Feed RSS Subscribe Inside the brief
What’s in today’s issue
6 items Today MCP TypeScript/Python SDKs: cross-origin redirect credential leak and an experimental task cross-session bug (2 Oct) Essay AI On 2 October the MCP reference SDKs published three repository advisories. Two cover the same client-transport flaw in… Essay Tech Why it matters: Spend limits are egress and blast-radius controls for autonomous tool use, the financial twin of… 4 items Also noted Altman vs "religious force": Axios (3 Oct): Sam Altman says ascribing religious force or surrender of human judgment…
Previously
Recent issues
Issue #07 Eval sandboxes, MCP credentials, and agent cloud computers UK AISI hardens and restarts most dangerous-capability evals, official MCP client SDKs disclose OAuth issuer-trust flaws, and dedicated agent cloud computers raise the question of who decides what leaves the box. 11 items 6 min 5 sections Issue #06 Eval sandboxes harden, attackers lead on AI, banks scale Claude UK AISI restarts most dangerous-capability evaluations after a security rebuild, Microsoft says attackers are capturing AI speed first, OpenAI details a distillation campaign, and Barclays plus Claude Code mods sharpen the enterprise control-plane story. 13 items 6 min Issue #05 Gemini 4 Argon, a Moonshot distillation campaign, and rails for paying agents Google opens Gemini 4 Argon to trusted cyber defenders first, OpenAI says it disrupted a July distillation campaign tied to a Moonshot cluster, and Cloudflare and Microsoft ship clearer rails for paying agents and approving MCP tools. 8 items 6 min Issue #04 OpenAI DevDay: Dots, Astra hold, Sol, and GLM-5.3 cyber OpenAI's DevDay puts always-on Dots agents and the cheaper GPT-6.1 Sol on the table while GPT-6.1 Astra stays withheld, and Anthropic warns that open-weight GLM-5.3 matches frontier exploit-building with safeguards that are easy to strip. 10 items 6 min Issue #03 AI / tech daily digest – Tuesday 29 September 2026 OpenAI shelves GPT-6.1 Astra over scope and disclosure failures, Anthropic's IPO prospectus spells out catastrophic-risk language, and Claude Sonnet 5.5 ships with Opus-class cyber safeguards. 9 items 5 min