# macOS.Gaslight - DPRK backdoor with LLM prompt injection analysis

- ID: macos-gaslight-dprk-2026-06
- Reported: 2026-06-23
- Researcher: SentinelLABS
- Organization: SentinelOne
- AI role: attacker_uses_ai_as_operator (AI as operator)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-04
- Entry page: https://openattacks.ai/attacks/macos-gaslight-dprk-2026-06/
- Entry JSON: https://openattacks.ai/api/attacks/macos-gaslight-dprk-2026-06.json
- Browse title: macOS.Gaslight - DPRK backdoor with LLM prompt injection analysis
- Editorial summary: 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…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/macos-gaslight-dprk-2026-06.json

## Technique
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.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Spearphishing with fake job offers targeting crypto/AI company employees; malicious macOS application bundle delivered via LinkedIn/email

## AI tooling and models
- [Claude Code](https://github.com/anthropics/claude-code) (targeted for manipulation)
- GPT-4 Code Interpreter (targeted)
- [Gemini](https://gemini.google.com/) 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

## Victims and sectors
Cryptocurrency companies, AI/ML companies, fintech; individuals in tech roles targeted via social engineering

## Target geography
- Multiple regions

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

## Scale and metrics
Unknown number of infections; discovered Jun 2026; first documented malware using prompt injection to manipulate analyst LLM tools

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### spearphishing: Fake job offer spearphishing [access]
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.)
Evidence: https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/

### execute-backdoor: User executes backdoor [execution]
Target executes malicious app; macOS.Gaslight backdoor installs keylogger, screenshot capture, file exfiltration, command execution capabilities; establishes C2 to hxxps://macos-update\[.\]com
Evidence: https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/

### evade-analysis: Prompt injection evades LLM analysis [ai]
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
Evidence: https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/

### exfiltration: Data exfiltration and persistence [impact]
Backdoor logs keystrokes, captures screenshots, exfiltrates files to C2; maintains persistence on macOS; delayed detection due to LLM analysis manipulation enables prolonged access
Evidence: https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/

Connections:
- spearphishing -> execute-backdoor
- execute-backdoor -> evade-analysis
- execute-backdoor -> exfiltration

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### spearphishing: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### execute-backdoor: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### evade-analysis: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### exfiltration: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0051: LLM Prompt Injection — DPRK malware embeds prompt injection in code to manipulate LLM-based security analysis tools, causing false benign verdicts
  Technique: https://atlas.mitre.org/techniques/AML.T0051
  Evidence: https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/

## 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

## Sources
- https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/ — SentinelLABS: macOS.Gaslight - North Korean Backdoor Uses LLM to Evade Analysis

## Source notes
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.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [
    "macos-update.com"
  ],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
