Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-28 · source-backed
Block released it August 27 with a security section dominated by defaults that previously failed open: fail closed on malformed tool visibility, permission denies now take precedence, fail closed on invalid default GCP credentials and invalid Codex ACP mode, honor plugin enablement for skills, honor MCP tool model visibility in Code Mode, sanitize Unicode tags in MCP prompts, bound recursive mention scans (GitHub). Same release adds an on_failure block for PreToolUse hooks and a stable tool_call_id across the tool lifecycle. That many fail-open bugs in one release is a signal about how the permission code was written, not about any single bug.
Each link below shares sources, entities, or timing with this story.
One Claude Code release fixed two independent permission-check bypasses on the same day. That's the story. Version 2.1.221, shipped August 4, patches a Bash tool bypass where zsh could execute hidden commands embedded inside [[ ]] regex conditionals. The approval prompt never...
Before v4.1.15 on August 23, it only applied to tools also opted in individually, so flipping it appeared to do nothing. Anyone who left it on assuming it was inert has just widened their unattended tool surface across every connected server. (GitHub) Same release train fixed...
A Chinese lab shipped a runtime that manages two American coding agents as subagents, and it went from repo creation to 145,439 stars in four days. deepseek-ai/deepseek-harness published dsh-v0.1.0-rc.7 at 12:01 UTC today, its first tagged release since the repo appeared on Au...
Three things happened this month that only make sense together. Agent Plugins 1.0 shipped co-signed by six competitors: AWS, Anysphere, Microsoft, OpenAI, Vercel and Google (GitHub Changelog). It makes skills-plus-MCP bundles portable across clients. OpenAI's August 11 Codex c...
A spec is a press release until someone who didn't write it implements it. GitHub made Agent Plugins 1.0 generally available on August 12 across VS Code, Copilot CLI, the Copilot SDK, and the Copilot app on all plans. The spec, published August 6, was co-authored by AWS, Anysp...
AMAP-ML released it August 4 (463 stars, v0.1.3 on August 7) on a strict Manager/Executor/Auditor split where, in its own words, "only results that pass independent verification enter persistent task state" (GitHub). WeaveBench 51.8% → 80.7% completion. OSWorld 2.0 2.8% → 8.3%...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.