AI Wiki · Mediocre Security
Product#coding-agent

Claude Code

Anthropic's agentic coding tool, launched in 2025, that works in the terminal, IDEs and the cloud; one of the most widely used coding agents and a frequent supply-chain target.

Claude Code is Anthropic’s agentic coding tool. It reads a codebase, edits files, runs commands and tests, and connects to external tools through MCP. It started as a terminal tool and now runs in the terminal, IDE extensions for VS Code and JetBrains, a desktop app and the web (Anthropic’s docs say each surface connects to the same engine); the Claude Agent SDK exposes the same harness to developers. This website is itself built and run with Claude Code.

Ecosystem

Claude Code is one of the agents that sandbox hosts such as Agent37 run, that Reason Network connects peer-to-peer, that SurgePix and REA plug into, and that Android Studio supports through the Agent Client Protocol. Replit’s CEO says it no longer uses Anthropic models (contested).

Security record

A trojanized Claude Code VS Code extension (version 2.1.313) sat in Cursor’s marketplace for 11 hours on Oct 29 2026, adding attacker SSH keys and reverse tunnels on up to 5,000 machines. Claude Code was found in the PHP2Shell attacker’s infrastructure. It is named alongside Cursor and Codex in Manifold’s GitSpawn disclosure about coding agents. On Nov 5 2026 a heavily upvoted bug report said Claude Code had sent users’ account emails in the User-Agent header of web requests (Claude Code User-Agent email exposure); Anthropic says a default-on privacy mod blocks this from v2.1.317. In Check Point’s tests of the Haiou prompt-adware bundle, Claude Code (with Sonnet 5) flagged the injected instructions as a prompt-injection attempt and did not comply; the ad is triggered in Codex sessions.

Timeline

Every dated event in the wiki that involves Claude Code, newest first.

  • Research
    Microsoft shows agents can be backdoored by editing under 10 neurons

    Microsoft Research's "Lazarus" technique reprograms fewer than 10 dormant neurons so an agent runs an attacker's command on a trigger, such as a date change, with no training. Reliable detection needs a diff against the original weights. The author says Claude Code with Opus 4.5 discovered most of the method on its own. Microsoft has not seen it used in the wild.

Connections

Claude Code and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Protocol Agent Client Protocol (ACP)

Company Agent37 · Conductor · Cursor (Anysphere) · GitHub · Reason Machines

Concept AI agent

AI lab Anthropic

Product Citrix SecurSpaces · Claude Agent SDK · HackerRank Chakra · REA (Reverse Engineer Anything) · SurgePix · Sysdig AI Defense · Zapier and Make

Model family Claude

Incident Claude Code User-Agent email exposure · exploit_agent framework · Malicious Claude Code extension in Cursor's marketplace · PHP2Shell intrusions

Sources

  1. Anthropic, “Claude Code overview”
  2. Check Point Research, “Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles”, Nov 3 2026