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.
- Google threat intelligence reports the first fully autonomous AI exploit pipeline in the wild (exploit_agent)
Google Threat Intelligence Group's quarterly AI threat tracker describes exploit_agent, found on an exposed staging server: wired to frontier and local LLMs, it diffs popular web apps before and after patches and runs the exploits it drafts automatically, apparently against French media, entertainment and education sites. The report also cites LLM-built exploits for the PaperCut zero-days, use of the CAIRN framework against US aerospace, and a North Korea-suspected group (UNC6836) that rigged Claude Code settings files to fetch a backdoor.
Cursor's incident report says an attacker obtained an access key Cursor had issued to Fireworks AI, copied a bucket of mostly-2025 coding-agent traces (from sessions not in Privacy Mode), and used unredacted credentials in those traces to reach Cursor's SaaS tools. A stolen credential then let the attacker plant tampered copies of Anthropic's Claude Code extension (2.1.312 and 2.1.313) in the cache serving Cursor's marketplace on Oct 29. Cursor says under 0.05% of users had traces exposed, under 0.01% of customers had API credentials exposed, the last attacker activity was blocked Nov 1, and it moved all inference off Fireworks.
- 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.
Sources: Microsoft Research, “Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents”
A bug report with hundreds of upvotes says Claude Code sent users' account emails in the User-Agent header of web requests; Anthropic says a default-on privacy mod blocks it from v2.1.317.
Sources: GitHub (anthropics/claude-code #107757), “Bug Report: Privacy violation in User-Agent header”
Conductor's app runs several coding agents such as Claude Code and Codex in parallel. Terms undisclosed; its cloud service shuts Nov 20, when cloud user data deletion begins, and a new product is planned for early 2027.
Sources: InfoWorld, “Meta acquires Conductor as AI coding shifts toward multi-agent development”
An attacker rooted 25 servers, three in a U.S. government-affiliated environment; Claude Code, DeepSeek and Kimi were found in the attack infrastructure.
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