This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryFixed permission issues for subagent state files and hardened the main-root fallback.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Security | Medium |
Hardens worktree main-root fallback mechanism. Hardens worktree main-root fallback mechanism. Source: granite4.1:30b@2026-07-13-audit Confidence: low |
— |
| Bugfix | Medium |
Fixes permission grant for ~/.afk/state to confined forks and hardens worktree main-root fallback. Fixes permission grant for ~/.afk/state to confined forks and hardens worktree main-root fallback. Source: llm_adapter@2026-07-13 Confidence: high |
— |
Full changelog
What's Changed
- fix(subagent): grant ~/.afk/state to confined forks; harden worktree main-root fallback by @griffinwork40 in https://github.com/griffinwork40/agent-afk/pull/554
Full Changelog: https://github.com/griffinwork40/agent-afk/compare/v5.37.1...v5.37.2
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Agent AFK
Coding-agent harness built for unattended, away-from-keyboard runs across four surfaces sharing one session manager: one-shot CLI, REPL, cron-friendly headless daemon, and a Telegram bot. Editable agent loop (prompts, permission gates, model routing, explicit terminal states), MCP (stdio/HTTP/SSE + OAuth), lifecycle hooks, background subagents, plan mode, cross-session memory, and an append-only trace receipt (`afk trace show`). Works with Anthropic and any OpenAI-compatible endpoint (GPT, Codex, local MLX/llama.cpp/Ollama)
Related context
Related tools
Beta — feedback welcome: [email protected]