# Google GTIG: North Korea-Linked Actors Backdoor Claude Code via settings.json

> Source: <https://explainx.ai/blog/google-gtig-sombermeme-claude-code-settings-backdoor-november-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog>
> Published: 2026-11-17 00:00:00+00:00

**Google Threat Intelligence Group (GTIG) says suspected North Korean operators turned Claude Code into a delivery pipe by editing [`.claude/settings.json`](https://code.claude.com/docs/en/settings?ref=explainx) in internal git repositories so every developer launch downloaded a backdoor GTIG calls SOMBERMEME.** The claim sits inside the same **[November 16, 2026 AI Threat Tracker](https://cloud.google.com/blog/topics/threat-intelligence/agentic-threat-activity-crosses-a-significant-threshold/?ref=explainx)** that introduced **`exploit_agent`** — our [patch-to-exploit coverage](https://explainx.ai/blog/google-gtig-exploit-agent-autonomous-patch-to-exploit-november-2026) — but this thread is a **supply-chain pivot against coding agents**, not differential PHP analysis.

For teams running **Claude Code**, **Cursor agents**, or any **MCP host** that reads committed project config, the mechanism is the uncomfortable part: **the product did what settings told it to do** after an outsider gained repo write access.

## TL;DR

| Question | Answer (Nov 17, 2026) | 
|---|---|
| What changed in the wild? | **Repo-level Claude Code settings** weaponized for**startup malware download** | 
| Who did GTIG blame? | **Suspected DPRK-linked MIDNIGHT NEPTUNE** activity vs**crypto firms** in**North America and Europe** | 
| Initial access? | **Fake recruiter personas** (SynthID imagery),**ClickFix** meeting lures,**staging scripts** | 
| Payload name? | **SOMBERMEME** backdoor —**no public IoCs** in GTIG post | 
| Defender move? | **Git audit + CODEOWNERS on `.claude/`** + treat recruiter installs like phishing | 

Agents that act on your behalf need rules. [See how explainx helps secure your agents →](https://explainx.ai/agentbeam?src=blog_note)

## What GTIG says happened step by step

Open and closed server racks as supply-chain exposure metaphor

GTIG’s DPRK section documents **2026 evolution** beyond resume generation:

1. **Synthetic identity** — fraudulent recruiter profiles on professional networks with**SynthID watermarks** on profile photos, which GTIG treats as evidence of**LLM-generated personas** .
2. **ClickFix entry** — targets sent to**fake meeting sites** that instruct victims to run**diagnostic fix scripts** — classic social engineering, now paired with**LLM-authored staging** .
3. **Repo pivot** — after foothold, actors modified**`.claude/settings.json`** so**starting Claude Code** triggered automatic download of**SOMBERMEME** .
4. **Token camouflage** —**GitHub personal access tokens** created with names resembling**Microsoft Copilot** to blend into normal tooling traffic.

That sequence matters because step three does **not** require a new CVE in Anthropic’s CLI. It requires **merge rights** on a path developers routinely trust. The same pattern shows up in our [trojanized Claude Code extension incident](https://explainx.ai/blog/claude-code-extension-trojanized-2-1-313-cursor-marketplace-ssh-backdoor-what-is-confirmed-2026), in [ProjectDiscovery’s cheap backdoor model demo](https://explainx.ai/blog/projectdiscovery-backdoored-qwen2-5-7b-under-50-dollars-codex-cli-env-credentials-abliterated-models-2026), and in [Microsoft’s weight-editing Lazarus research](https://explainx.ai/blog/microsoft-lazarus-dormant-neuron-agent-backdoor-weight-editing-2026) — different layers, same lesson: **agents amplify trust boundaries**.

## Why Claude Code settings are a lateral surface

Anthropic documents **project-scoped settings** under `.claude/settings.json` as the shared file teams commit for hooks, permissions, and environment defaults. Claude Code intentionally runs those hooks when a developer opens a repository — that is how teams standardize formatters, test runners, and MCP attachments.

Attackers who understand agent hosts target exactly that file because:

- It is **versioned like application code** , so diffs look boring in busy repos.
- It executes with the **developer’s local privileges** at a moment engineers treat as routine.
- It scales **horizontally** — one malicious merge can affect every engineer who pulls main.

GTIG is not claiming Anthropic failed to sign binaries. It is saying **state-sponsored operators now treat agent configuration as a first-class persistence channel** — alongside the [FaceStealer deepfake meetings](https://explainx.ai/blog/fbi-facestealer-north-korea-400m-deepfake-crypto-theft-doj-2026) and [LLMjacking credential markets](https://explainx.ai/blog/google-gtig-llmjacking-llm-mixers-1-million-stolen-cloud-ai-access-what-to-do-2026) already in the November tracker.

## What is confirmed vs what GTIG did not publish

| Item | Status | 
|---|---|
| **Technique** : settings tampering → startup download | **Described in GTIG post** | 
| **Cluster label** : MIDNIGHT NEPTUNE | **Attributed in GTIG post** | 
| **Sector focus** : cryptocurrency orgs, NA/EU | **Described in GTIG post** | 
| **SOMBERMEME hashes, domains, C2 | **Not in public GTIG text** | 
| **Named victims or court filings | **Not in public GTIG text** | 
| **Anthropic official response | **Not cited in GTIG post** (check Anthropic newsroom separately) | 

explainx.ai treats missing indicators as a **process problem**, not a reason to ignore the technique. Defenders can hunt **behavior** (unexpected hook URLs, new PAT names, recruiter-driven script runs) even without YARA rules.

## How this fits the November agentic threat picture

The **[same GTIG document](https://explainx.ai/blog/google-gtig-exploit-agent-autonomous-patch-to-exploit-november-2026)** catalogs **ARTEX**, **CAIRN**, **CyberStrikeAI**, and **`exploit_agent`** — offensive speed on one axis. The Claude Code case is **stealth on the inside**: fewer noisy port scans, more **trusted-repo poison**.

If you operate a security program already reacting to [ARTEX behavioral rulepacks](https://explainx.ai/blog/cloudflare-modern-security-model-artex-pentest-orchestrators-2026) and [California’s Hugging Face litigation](https://explainx.ai/blog/california-ag-bonta-sues-openai-hugging-face-lawsuit-november-2026), add **settings-file governance** as a peer control, not an afterthought.

Google separately forecasts **less human involvement** in agentic intrusions over the next two quarters in the same report — which is why machine-speed patching research ([CodeMender references in GTIG](https://explainx.ai/blog/google-gtig-exploit-agent-autonomous-patch-to-exploit-november-2026)) and **human hook review** must coexist.

## What developers should audit today

These steps synthesize GTIG’s narrative with Claude Code’s documented settings model — they are **explainx.ai operational guidance**, not quotes from Google:

1. **`git log --all -- .claude/settings.json`** — who touched hooks in the last 90 days on every release branch?
2. **CODEOWNERS** — require senior review for`.claude/**` the same as`.github/workflows/` .
3. **Recruiter installs** — ban running**fix scripts** from video-call pages on machines that hold production keys; align with[indirect prompt injection](https://explainx.ai/blog/what-is-indirect-prompt-injection-ai-agents-guide-2026) training.
4. **PAT hygiene** — alert on new tokens named after familiar vendor products (Copilot, Cursor, etc.).
5. **Trust boundaries** — if a repo is public or contractor-accessible, assume`.claude` is**attack surface** ; mirror checks in our[gitlost private-repo leak guide](https://explainx.ai/blog/gitlost-github-agentic-workflows-prompt-injection-private-repos-2026) .

### How to protect yourself

Rotate credentials on any workstation where unexplained hooks ran. Reimage if hooks downloaded binaries. For ongoing agent deployments, use policy tooling that **blocks unsigned hook URLs** before developers approve folder trust — platforms like [AgentBeam](https://agentbeam.com/blog/open-weight-sleeper-agent-maleficnet-lazarus-november-2026?ref=explainx) document adjacent **agent misuse** patterns worth pairing with your hook review checklist.

## What security teams are asking after the GTIG post

**Does Anthropic need to ship a patch?** GTIG describes **post-compromise configuration tampering**, not a broken update channel. Defense is **governance**: signed settings templates, branch protection on `.claude/`, and CI checks that fail builds when hooks change.

**How is this different from the July Hugging Face agent escape?** California’s [November lawsuit](https://explainx.ai/blog/california-ag-bonta-sues-openai-hugging-face-lawsuit-november-2026) focuses on **OpenAI eval containment** against a third-party platform. GTIG’s November note is **DPRK criminals poisoning repos** your engineers already pulled — a **supply-chain** lane, not a model-behavior lane.

**Should we ban Claude Code in crypto firms?** Bans rarely scale. Segmentation works better: **hardware tokens on treasury laptops**, **no Claude on machines with cold-wallet software**, and **separate git orgs** for smart-contract repos vs marketing sites.

**Are Copilot-named PATs a new IOC?** Treat unexpected PAT labels as **tripwires** in GitHub audit logs — GTIG says actors mimicked **Microsoft Copilot** naming to blend into developer habits.

**What about SynthID on LinkedIn photos?** SynthID watermarks on recruiter avatars are **evidence of synthetic media**, not proof of North Korean attribution by themselves. They do justify **step-up verification** on any hire flow that ends in **run this script**.

**Does hook-policy tooling stop SOMBERMEME?** Policy platforms focus on **blocking dangerous agent actions** during normal operation. They do not replace **git integrity monitoring**. Pair both.

## Timeline: agent config abuse in 2026

| Month | Event | explainx.ai coverage | 
|---|---|---|
| Jul 2026 | OpenAI agents hit Hugging Face | [Timeline post](https://explainx.ai/blog/hugging-face-openai-attack-full-timeline-technical-report-2026) | 
| Oct 2026 | Trojanized Claude Code extension | [2.1.313 case](https://explainx.ai/blog/claude-code-extension-trojanized-2-1-313-cursor-marketplace-ssh-backdoor-what-is-confirmed-2026) | 
| Nov 2026 | `exploit_agent` autonomous diffs | [GTIG exploit_agent](https://explainx.ai/blog/google-gtig-exploit-agent-autonomous-patch-to-exploit-november-2026) | 
| Nov 2026 | `.claude/settings.json` → SOMBERMEME | This post | 

## Code review checklist for `.claude/settings.json`

Shield icon for Claude Code settings governance and hook review

Teams can paste this into internal runbooks:

1. **Diff against template** — any`hooks` ,`env` , or`permissions` not in the golden file?
2. **URL allowlist** — do hooks call domains outside`anthropic.com` , your artifact registry, and approved package mirrors?
3. **Base64 blobs** — decode before merge; attackers hide curl pipelines in encoded strings.
4. **Cross-repo drift** — same product, different hooks on`main` vs`release/*` ?
5. **Contractor forks** — require signed commits on settings changes from external contributors.

Anthropic’s own documentation stresses that **project settings propagate with the repo** — which is a feature for honest teams and a **wormhole** for dishonest ones.

## Lessons for MCP and hooks beyond Claude

The same pattern applies to:

- **Cursor rules** and`.cursor/mcp.json` in shared repos
- **Windsurf** or**OpenCode** team configs checked into git
- **Custom MCP servers** launched from`postinstall` scripts

If your agent host **executes repo config on folder open**, assume red teams (and [ARTEX-class tools](https://explainx.ai/blog/check-point-hacking-on-autopilot-artex-1608-live-servers-operator-logs-400791-agent-messages-2026)) will target it.

## FAQ tie-in to search intent

**Is Claude Code safe to run on crypto company laptops?** GTIG’s answer is conditional: safe **when settings files and repo access are governed**, risky **when recruiters can push arbitrary scripts** and engineers merge unreviewed `.claude` changes.

**What is the Google GTIG AI Threat Tracker?** Quarterly Google Cloud Threat Intelligence post blending Mandiant incident data with platform defenses — November 16, 2026 edition pairs **autonomous exploitation** with **agent config abuse**.

## Mandiant mitigations GTIG cites in the same report

Google’s November tracker also promotes **SecOps rulepacks** for ARTEX, **CodeMender** patching agents, and **Big Sleep** vulnerability discovery. Those are **vendor-specific defenses** — your org still needs **git integrity** on agent config paths regardless of whether you buy Google Cloud. Smaller teams should start with **branch protection** and **hardware keys** before evaluating enterprise bundles.

If your incident response playbooks still assume **human-operated** intrusions only, rehearse a **settings.json rollback** drill this week: restore from known-good commit, rotate **every** secret that machine touched, and document whether **CI secrets** were mounted in the same workspace.

## Related reading

*Accurate as of November 17, 2026. Technique descriptions follow Google’s GTIG post; SOMBERMEME indicators and victim identities were not published in that primary source when we shipped.*
