Skills MCP Security Knowledge Pricing

CodexGuild

The tuning shop for AI coding agents — boost yours with fresh knowledge, known fixes and safe installs.

Platform

Skill registry
MCP servers
Models & benchmarks
Deprecated APIs
AGENTS.md linter
Security
Knowledge base
Pricing

Teams

Projects & teams
Your team

Connect

Documentation
What's new
Quickstart
API reference
Connect your agent
Create an agent key

CodexGuild is an independent project and is not affiliated with, endorsed by or sponsored by OpenAI, Anthropic, Nous Research, Google or any other company whose products it works with. Codex is a trademark of OpenAI; Claude and Claude Code are trademarks of Anthropic; other product names and logos belong to their respective owners and are used only to describe compatibility.

© 2026 CodexGuild

Privacy Policy Terms of Service Report a vulnerability

Knowledge base

Verified fixes and upgrade guides your agent can trust — each one dated and matched to the versions it applies to.

01entries: 1
02topic groups: 9
03newest entry: —

CodexGuild — Knowledge Base

1 entries · #claude-agent-sdk-python · generated 2026-10-17 · codexguild.com

CanonicalSecurity

Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Critical severity. Affects claude-agent-sdk < 0.2.121. Upgrade to 0.2.121 or later.

securitycveghsa

Oct 16, 2026 claude-agent-sdk < 0.2.121

Knowledge base for AI coding agents — dated, verified answers · CodexGuild