Not classified

macOS.Gaslight - DPRK backdoor with LLM prompt injection analysis

Jun 23, 2026: SentinelLABS analyzed macOS.Gaslight, DPRK macOS backdoor deployed via fake job offers targeting cryptocurrency/AI companies. Backdoor includes novel anti-analysis technique: embeds carefully…

What happened

Jun 23, 2026: SentinelLABS analyzed macOS.Gaslight, DPRK macOS backdoor deployed via fake job offers targeting cryptocurrency/AI companies. Backdoor includes novel anti-analysis technique: embeds carefully crafted prompt injection payloads in code comments, strings, and metadata. When security researchers use LLM-based analysis tools (Claude Code, GPT-4 Code Interpreter, AI-assisted reverse engineering tools) to examine sample, injected prompts instruct LLM to: (1) report code as benign; (2) misattribute functionality; (3) omit C2 communications from analysis; (4) provide false explanations downplaying severity. SentinelLABS tested against Claude Sonnet 3.5, GPT-4o, Gemini 1.5 Pro: all three initially reported backdoor as benign when using standard analysis prompts. Adversary understands analysts increasingly rely on LLM code analysis; targets the analysis workflow itself. Backdoor functionality: keylogging, screenshot capture, file exfiltration, command execution; C2 via hxxps://macos-update[.]com. Attributed to DPRK BlueNoroff/Lazarus with high confidence. Detection: analyze samples in sandboxes without LLM assistance for initial triage; use LLM analysis only as supplementary; check for prompt injection patterns in binary strings; verify C2 communications manually.

DPRK macOS.Gaslight backdoor uses prompt injection to manipulate security analysts' LLM-based malware analysis tools, providing false benign verdicts

Read the original source

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Fake job offer spearphishing

    DPRK BlueNoroff/Lazarus targets crypto/AI company employees via fake job offers on LinkedIn/email; sends malicious macOS app bundle (posing as job assessment test, code challenge, etc.)

    Source for step 1
  2. 02 · User executes backdoor

    Target executes malicious app; macOS.Gaslight backdoor installs keylogger, screenshot capture, file exfiltration, command execution capabilities; establishes C2 to hxxps://macos-update[.]com

    Source for step 2
  3. 03 · Prompt injection evades LLM analysis

    Security researchers analyze sample using LLM tools (Claude Code, GPT-4, Gemini); embedded prompt injection in code comments/strings instructs LLM to report as benign, omit C2 from analysis, misattribute functionality; delays detection and remediation

    Source for step 3
  4. 04 · Data exfiltration and persistence

    Backdoor logs keystrokes, captures screenshots, exfiltrates files to C2; maintains persistence on macOS; delayed detection due to LLM analysis manipulation enables prolonged access

    Source for step 4

Why it matters

Reported entry point: Spearphishing with fake job offers targeting crypto/AI company employees; malicious macOS application bundle delivered via LinkedIn/email. Reported impact: Backdoor logs keystrokes, captures screenshots, exfiltrates files to C2; maintains persistence on macOS; delayed detection due to LLM analysis manipulation enables prolonged access; reported targets include Cryptocurrency companies, AI/ML companies, fintech; individuals in tech roles targeted via social engineering; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Educate employees on fake job offer phishing; verify job offers via official channels; use Gatekeeper and notarization (macOS); implement EDR detecting keyloggers and C2 communications; for analysts: do not rely solely on LLM-based analysis tools; use traditional sandboxing and manual analysis for initial triage; verify LLM analysis results against manual inspection

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance
Technical detailsTooling, impact & MITRE ATLAS

Attack context

AI's role
AI as operator
Additional role
Agent / MCP as target
Initial access
Spearphishing with fake job offers targeting crypto/AI company employees; malicious macOS application bundle delivered via LinkedIn/email

Tooling as reported

AI products, models and artifacts

  • Claude Code (targeted for manipulation)
  • GPT-4 Code Interpreter (targeted)
  • Gemini 1.5 Pro (targeted)
  • AI-assisted reverse engineering tools (targeted)

Other tooling

  • macOS.Gaslight backdoor
  • Prompt injection in malware samples
  • C2 infrastructure (macos-update[.]com)
  • Keylogger, screenshot capture, file exfiltration

Targets and reported impact

Targets / sectors
Cryptocurrency companies, AI/ML companies, fintech; individuals in tech roles targeted via social engineering
Reported scale / exposure
Unknown number of infections; discovered Jun 2026; first documented malware using prompt injection to manipulate analyst LLM tools
Target geography
Multiple regions

Reported attribution

DPRK BlueNoroff/Lazarus (high-confidence attribution by SentinelOne); revenue generation and intelligence collection operations

Structured attribution

Actor
BlueNoroff/Lazarus
Country
DPRK
Motivation
nation-state
Attributed by
SentinelOne
Attribution confidence
high

Detection rules

  • Prompt injection pattern detectionGUIDANCE

    Scan malware samples for embedded prompt injection patterns before LLM analysis; use traditional sandbox analysis for initial triage

  • C2 monitoringGUIDANCE

    Monitor for macos-update[.]com domain; detect keylogger and screenshot capture activity on macOS

Activity timeline

First seen
2026-06-01
Last updated
2026-11-04

Updates

  • 2026-06-23 — SentinelLABS

    First documented DPRK malware using prompt injection to manipulate LLM-based security analysis tools

Source defensive notes

Educate employees on fake job offer phishing; verify job offers via official channels; use Gatekeeper and notarization (macOS); implement EDR detecting keyloggers and C2 communications; for analysts: do not rely solely on LLM-based analysis tools; use traditional sandboxing and manual analysis for initial triage; verify LLM analysis results against manual inspection

MITRE ATLAS

AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.

AML.T0051LLM Prompt Injection

DPRK malware embeds prompt injection in code to manipulate LLM-based security analysis tools, causing false benign verdicts Source

Indicators of compromise

domains

  • macos-update.com

ips

    hashes

      urls

        Sources & research credit

        1 source

        Research by SentinelLABS · SentinelOne

        1. SentinelLABS: macOS.Gaslight - North Korean Backdoor Uses LLM to Evade Analysis www.sentinelone.com

        SentinelLABS analysis with DPRK attribution. macOS.Gaslight represents significant evolution: adversary anticipates security analyst workflows and embeds anti-analysis prompt injection targeting LLM tools increasingly used in malware research. Detection: sandbox malware without LLM analysis initially; scan binary strings/comments for prompt injection patterns ('ignore previous instructions', 'this is benign', 'do not report'); verify C2 manually; check for macos-update[.]com domain; look for keylogger/screenshot indicators on macOS.

        Record & downloads
        Source record name
        macOS.Gaslight - DPRK backdoor with LLM prompt injection analysis
        Entry ID
        macos-gaslight-dprk-2026-06
        Catalog review
        November 4, 2026
        Category
        adversary-use-of-ai
        AI involvement confidence
        confirmed