This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryFixed handling of NaN config values, non‑string systemPrompt entries, and masked registry‑skill errors.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Bugfix | Medium |
Guard against NaN config, non-string systemPrompt, and unmask registry-skill errors. Guard against NaN config, non-string systemPrompt, and unmask registry-skill errors. Source: llm_adapter@2026-07-13 Confidence: low |
— |
| Bugfix | Low |
Guard against NaN config values. Guard against NaN config values. Source: granite4.1:30b@2026-07-13-audit Confidence: low |
— |
| Bugfix | Low |
Ensure systemPrompt is a string. Ensure systemPrompt is a string. Source: granite4.1:30b@2026-07-13-audit Confidence: low |
— |
| Bugfix | Low |
Unmask errors from registry-skill lookups. Unmask errors from registry-skill lookups. Source: granite4.1:30b@2026-07-13-audit Confidence: low |
— |
Full changelog
What's Changed
- fix(config,skills): guard NaN config + non-string systemPrompt + unmask registry-skill errors by @griffinwork40 in https://github.com/griffinwork40/agent-afk/pull/534
Full Changelog: https://github.com/griffinwork40/agent-afk/compare/v5.33.1...v5.33.2
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]