explainx.ai350K+ learn from us
TrendingAI News TodayPathwaysSkills
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

follow on google

Add explainx.ai as a preferred source

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

community

Join the community

learn

mind: share how you thinkpathways — start freeworkshopsbootcampscoursescompare Explainxcertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcpestacktoolsmdx readeragentsllmsdesignsdictionarypeopleagi trackerfelony benchranks

company

aboutvisionmissionteaminstructorsteach on explainxpartnershipscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

explainx.ai

On this page

  • TL;DR
  • What GTIG says happened step by step
  • Why Claude Code settings are a lateral surface
  • What is confirmed vs what GTIG did not publish
  • How this fits the November agentic threat picture
  • What developers should audit today
  • What security teams are asking after the GTIG post
  • Timeline: agent config abuse in 2026
  • Code review checklist for .claude/settings.json
  • Lessons for MCP and hooks beyond Claude
  • FAQ tie-in to search intent
  • Mandiant mitigations GTIG cites in the same report
  • Related reading
← Back to blog

explainx / blog

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

Cybersecurity, Claude Code, Google, North Korea, AI Agents

Part of AI Security

Google Threat Intelligence Group says a suspected DPRK cluster edited .claude/settings.json so Claude Code downloads the SOMBERMEME backdoor at launch. What GTIG confirms and how teams audit hooks.

Nov 17, 2026·8 min read·Yash Thakker
add explainx.ai
go deep
Google GTIG: North Korea-Linked Actors Backdoor Claude Code via settings.json

Google Threat Intelligence Group (GTIG) says suspected North Korean operators turned Claude Code into a delivery pipe by editing .claude/settings.json 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 that introduced exploit_agent — our patch-to-exploit coverage — 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

table · 2 cols
QuestionAnswer (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
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

Agents that act on your behalf need rules. See how explainx helps secure your agents →

What GTIG says happened step by step

Open and closed server racks as supply-chain exposure metaphorOpen 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, in ProjectDiscovery’s cheap backdoor model demo, and in Microsoft’s weight-editing Lazarus research — 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 and LLMjacking credential markets already in the November tracker.

What is confirmed vs what GTIG did not publish

table · 2 cols
ItemStatus
Technique: settings tampering → startup downloadDescribed in GTIG post
Cluster label: MIDNIGHT NEPTUNEAttributed in GTIG post
Sector focus: cryptocurrency orgs, NA/EUDescribed in GTIG post
**SOMBERMEME hashes, domains, C2Not in public GTIG text
**Named victims or court filingsNot in public GTIG text
**Anthropic official responseNot 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 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 and California’s Hugging Face litigation, 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) 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 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.

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 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 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

table · 3 cols
MonthEventexplainx.ai coverage
Jul 2026OpenAI agents hit Hugging FaceTimeline post
Oct 2026Trojanized Claude Code extension2.1.313 case
Nov 2026exploit_agent autonomous diffsGTIG exploit_agent
Nov 2026.claude/settings.json → SOMBERMEMEThis post

Code review checklist for .claude/settings.json

Shield icon for Claude Code settings governance and hook reviewShield 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) 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

  • Google GTIG exploit_agent: autonomous patch-to-exploit pipeline
  • Trojanized Claude Code extension 2.1.313
  • FBI FaceStealer and DPRK deepfake meetings
  • Cloudflare’s six layers vs ARTEX-style agents
  • Hugging Face OpenAI agent attack timeline
  • November 2026 cyberattacks tracker

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.

Spotted something out of date? Let us know.
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

  • ✓ Free
  • ✓ One email a day, no spam
  • ✓ Unsubscribe anytime
Yash Thakker

Written by

Yash Thakker

Yash is an AI expert with over 300K learners. Join his workshops →

View Yash Thakker in People in AI →

Related posts

Nov 16, 2026

Google GTIG exploit_agent: First Fully Autonomous Patch-to-Exploit Pipeline

On November 16, 2026 Google Threat Intelligence Group reported the first observed fully autonomous vulnerability pipeline. A staging server hosted exploit_agent, wired to frontier and local LLMs, comparing web app code before and after patches, writing exploits, and executing them with Russian-language operator notes.

Aug 22, 2026

Google Antigravity Remote Control: Browser-Based Agent Sessions Explained

Google Antigravity's Remote Control lets you connect to agent sessions running on any of your machines from a web browser, with push notifications and full local context. Ultra subscribers get it first, rolling out to all. Here is what it actually does and how it stacks up against Claude Code's phone-based remote control, which got its own reliability update the day before.

Nov 15, 2026

ChatMate and Remote Prompt Execution: Copilot Sandbox Escape Explained

Researchers at Rubrik Zero Labs demonstrated ChatMate, the first public Remote Prompt Execution chain against Microsoft 365 Copilot. A malicious document can trigger code in Copilot's interpreter, escape Azure Dynamic Sessions, and hand an attacker a bidirectional prompt channel that runs with the victim's identity. Microsoft fixed the host escape as CVE-2026-32193 before disclosure.