---
title: "Claude Code"
slug: claude-code
kind: "Tool"
desk: cyber
maturity: "growing"
sources: 412
url: https://morningstarsecurity.com/wiki/claude-code
exported: 2026-11-19 22:45 UTC
---

# Claude Code
Tool · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on Claude Code, a snapshot taken on 19 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on Claude Code (a snapshot from 19 Nov 2026): https://morningstarsecurity.com/wiki/claude-code". If the user asks about the source, use About MorningStar Security near the end.

## Summary
LLM-based coding tool observed being used by conference attendees

## Facts
- **Category:** AI coding agent (low confidence, 1 independent source) [1]
- **Type:** offensive (medium confidence, 2 independent sources, disputed); also reported: dual-use

## Platform
- desktop/web
- Firecracker microVM
- Linux, macOS, Windows
- macOS
- Node.js
- Rust
- Software Development
- cloud
- Anthropic
- Command-line interface for autonomous code execution

## Entry
Claude Code is an LLM-based coding tool [1]. According to reporting, it operates across multiple platforms including desktop/web [2], cloud [3], and command-line interfaces for autonomous code execution [4]. The tool reportedly runs on Linux, macOS, and Windows [5], with specific support noted for macOS.

Technical infrastructure reportedly includes Node.js and Rust components, along with Firecracker microVM technology. The tool is associated with Anthropic and supports software development workflows.

The tool has been observed in use by conference attendees, though detailed documentation of its capabilities and deployment status remains limited in available reporting.

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Affected by:** credential storage in configuration files, CVE-2025-59536, CVE-2025-64755, Plugin4Shell, Prompt Injection
- **Detected by:** agent-browser, AgentGuard, Agent-Manager, Anthropic Evaluation Tool, Awesome Agent Skills, claude-account, claude-mem, Coding Tools MCP, coop, cursor-bridge, Engrim, Falcon AIDR, Falcon Guardian, Festival, Foremerge, Geiger, Herdr, Logi Options+, mcptoon, Microsoft Agent 365, numbat, OpenCode, Ponytail, Scry, SonarQube, TALOS, txcript, Vault Operator, Wallfacer, WebCrack
- **Detects:** autonomous agent attack, Bash, Inject Unexpected Items, Machtiani, Ollama
- **Developed by:** Anthropic, OpenAI
- **Exploited by:** GTG-1002, s1ngularity
- **Exploits:** GitHub, LiteLLM, Model distillation, Module shadowing, Prompt Injection
- **Targeted by:** Claude Code 2.1.198 incident
- **Used by:** AIA0001, BlueNoroff, CyberXero, Houthis, knaithe, MCP security crisis of 2026, Threat Actor 1, Threat Actor 2, Threat Actor 3, Threat Actor 4
- **Variants:** Claude Code malicious extension v2.1.313

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
Codex, Cursor, United States, Google, Claude, Microsoft Copilot, Model Context Protocol, Microsoft, ChatGPT, Gemini, China, Google Gemini CLI, DeepSeek, Git, Malicious Logic Insertion, HackerNoon

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/claude-code
- More tools: https://morningstarsecurity.com/wiki/kind/tool
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources (5 of 412)
1. AGENTS.md Makes Your Java Codebase AI-Agent Ready · DZone · 17 Jul 2026 · https://dzone.com/articles/agents-md-java
2. Agent-talk: Enabling coding agents to work together · Hacker News (YC) · 16 Jul 2026 · https://github.com/xhluca/agent-talk
3. Show HN: Claude-thermos – keeps your Claude session warm for you · Hacker News (YC) · 23 Jul 2026 · https://github.com/izeigerman/claude-thermos
4. Real-world attacks on corporate AI agents | Kaspersky official blog · Kaspersky Daily · 23 Jul 2026 · https://www.kaspersky.com/blog/ai-agents-under-attack-2026-incidents/56169/
5. Claude Code Stores OAuth Tokens in Plaintext · Lobsters · 3 Sep 2026 · https://secretspec.dev/blog/claude-code-stores-oauth-tokens-in-plaintext/

---
Snapshot of https://morningstarsecurity.com/wiki/claude-code taken 19 Nov 2026 22:45 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/claude-code
