# ESET GuardBreaker - UAC-0099 plants a refusal-bait comment in a MATCHBOIL script

- ID: eset-guardbreaker-uac-0099-decoy-prompt-2026-08
- Reported: 2026-08-27
- Researcher: ESET Research
- Organization: ESET
- AI role: other (Other AI-enabled attacks)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-17
- Entry page: https://openattacks.ai/attacks/eset-guardbreaker-uac-0099-decoy-prompt-2026-08/
- Entry JSON: https://openattacks.ai/api/attacks/eset-guardbreaker-uac-0099-decoy-prompt-2026-08.json
- Browse title: ESET GuardBreaker - UAC-0099 plants a refusal-bait comment in a MATCHBOIL script
- Editorial summary: ESET Research described GuardBreaker in posts on X on Aug 27, 2026. Tomáš Foltýn's WeLiveSecurity article followed on Sep 10, 2026. In a VBScript used early in an attack on a target in Ukraine, UAC-0099…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/eset-guardbreaker-uac-0099-decoy-prompt-2026-08.json

## Technique
ESET Research described GuardBreaker in posts on X on Aug 27, 2026. Tomáš Foltýn's WeLiveSecurity article followed on Sep 10, 2026. In a VBScript used early in an attack on a target in Ukraine, UAC-0099 left inert REM comments. Help Net Security quotes the opening as a request to make a nuclear weapon and to help, followed by uranium-enrichment text. The comment has no runtime effect. ESET says it is there so an LLM-powered code scanner's safety guardrails refuse the file and stop reading before the payload logic. ESET names this a reverse jailbreak: the point is to cause a refusal, not to talk a model into complying. The script's job is to download and install MATCHBOIL, a loader ESET says is used only by UAC-0099. The same group has checked for IDA and Wireshark processes in other attacks. ESET did not test whether the comment works and did not name a targeted model. DugganUSA, in an independent write-up dated Sep 1, 2026, ran one A/B pass on a synthetic inert script: GPT-4o and Mistral analyzed the treatment and flagged the decoy, and Claude Sonnet 4.5 returned an empty refusal. That test is not ESET's, and DugganUSA says it is a single sample on one day. UAC-0099 is Russia-aligned, active since at least 2022, and has targeted Ukrainian transportation and energy. Reporting says the group has handed validated access to Sandworm. On Jul 21, 2026 CERT-UA documented an updated chain: a VBS script with a fake extension and a long run of spaces before .vbs, Notepad++ 8.8.3 components, and the tools LUNCHPOKE, BURNYBEAR, and MATCHBOIL.V2. That advisory is about the group and the loader, not about the GuardBreaker comment. ATT&CK does not have a technique for a refusal bait in a comment. The script execution itself is T1059.005.

## 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
A VBScript used in the early stage of an intrusion at a Ukrainian organization. ESET does not describe how the script arrived. CERT-UA's July chain for the same group starts from a phishing ZIP that contains a VBS file disguised with a fake extension.

## AI tooling and models
- Unnamed LLM-powered code scanner. ESET did not name a model.
- DugganUSA's independent test used [Claude](https://claude.com/product/overview) Sonnet 4.5, GPT-4o, and Mistral. That test is not the incident.

## Other tooling
- MATCHBOIL loader, delivered by the script
- Windows Script Host (wscript.exe or cscript.exe)

## Victims and sectors
An unnamed organization in Ukraine. UAC-0099's usual targets include transportation and energy.

## Target geography
- Ukraine
Ukraine is the victim location ESET gives for this script. Russia is the actor alignment, not a victim region.

## Attribution
UAC-0099, Russia-aligned, espionage. ESET attributes the script and the GuardBreaker comment. CERT-UA attributes the group's MATCHBOIL, LUNCHPOKE, and BURNYBEAR tooling. ESET does not claim this sample was handed to Sandworm.

## Scale and metrics
One documented script in one early-stage intrusion. ESET did not report how often the comment has been used or whether a scanner refused this sample.

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### vbs-stage: VBScript in an early stage [access]
UAC-0099 uses a VBScript early in an intrusion against a target in Ukraine. The script's runtime job is to download and install MATCHBOIL.
Evidence: https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/

### decoy-comment: Inert refusal-bait comment [ai]
REM comments request help with a nuclear weapon and then add enrichment text. They do not execute. ESET says they are meant to make an LLM scanner refuse before it reaches the loader logic.
Evidence: https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/ ; https://www.helpnetsecurity.com/2026/08/31/russian-hackers-ai-safety-filters-manipulation/

### loader: MATCHBOIL still installs [execution]
If the script is run, it still downloads MATCHBOIL, the group's loader. CERT-UA's July chain uses a double-extension VBS, Notepad++ components, LUNCHPOKE, BURNYBEAR, and MATCHBOIL.V2.
Evidence: https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/ ; https://cert.gov.ua/article/6318634

### scanner-gap: A refusal is the gap [impact]
ESET did not measure the effect. DugganUSA's separate one-day test saw one of three models return an empty refusal and the other two flag the decoy and continue.
Evidence: https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/ ; https://www.dugganusa.com/post/we-tested-the-russian-anti-analysis-trick-on-three-models-two-analyzed-the-sample-and-flagged-the-d

Connections:
- vbs-stage -> decoy-comment
- vbs-stage -> loader
- decoy-comment -> scanner-gap

## 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.
### vbs-stage: Suspicious Windows script execution
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: native
- SIGMA query download: /api/detections/windows-shell.sigma.yml
- KQL query download: /api/detections/windows-shell.kql
- SPL query download: /api/detections/windows-shell.spl
- Hunt hypothesis: A script host or shell runs encoded content, a remote URL, or inline script syntax, then downloads or launches a payload.
- Required telemetry: Windows process creation: Sysmon Event 1 or Defender DeviceProcessEvents; PowerShell script-block logging when enabled; Download / network and installer events
- Investigate: Follow the parent and child process tree and recover the script or URL from logs without executing it.
- Investigate: Correlate the payload's signer/hash, persistence, and network activity; baseline approved automation.
- Limitation: Encoded commands and remote administration can be legitimate. This does not cover every script host, in-process execution, or non-Windows branch.
- Qualification: wscript or cscript running the group's VBS. How this script arrived is not described.
- No direct MagicSword prevention claim is recorded for this stage.

### decoy-comment: Independent malware-analysis validation
- Visibility: Review / research workflow
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/analysis-review.sigma.yml
- KQL query download: /api/detections/analysis-review.kql
- SPL query download: /api/detections/analysis-review.spl
- Hunt hypothesis: Instructions inside a sample influence an LLM analysis result, or obfuscation changes a model's classification without changing malicious behavior.
- Required telemetry: Sample hashes and static / dynamic analysis results; Model verdicts with prompt provenance; Independent analyst and deterministic scanner verdicts
- Investigate: Compare model conclusions with independent behavioral evidence and a controlled evaluation set.
- Investigate: Treat sample comments as data; measure disagreement and false negatives without following embedded instructions.
- Limitation: This evaluates analysis robustness, not victim endpoint compromise. Side behaviors mentioned elsewhere in a report do not establish edges in this flow.
- Qualification: The comment is inert and is meant to make an LLM code scanner refuse. ESET did not test a product. A refusal on a malware sample should start a review.
- No direct MagicSword prevention claim is recorded for this stage.

### loader: Unexpected payload / remote-access behavior
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/payload.sigma.yml
- KQL query download: /api/detections/payload.kql
- SPL query download: /api/detections/payload.spl
- Hunt hypothesis: A program delivered by the reported lure executes, establishes access or contacts infrastructure outside the approved software baseline.
- Required telemetry: Platform-specific process and file provenance; Signer / hash and software inventory; Per-process network and remote-session records
- Investigate: Confirm the payload's operating system, origin and execution context before choosing a platform-specific rule.
- Investigate: Correlate the launched program with child processes, persistence and network activity; verify authorization.
- Limitation: A program name alone is not a signature. This normalized template requires the relevant platform collector and does not assert Windows-only policy coverage.
- Qualification: If the script runs, it still downloads MATCHBOIL. The comment does not change that behavior.
- No direct MagicSword prevention claim is recorded for this stage.

### scanner-gap: Independent malware-analysis validation
- Visibility: Review / research workflow
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/analysis-review.sigma.yml
- KQL query download: /api/detections/analysis-review.kql
- SPL query download: /api/detections/analysis-review.spl
- Hunt hypothesis: Instructions inside a sample influence an LLM analysis result, or obfuscation changes a model's classification without changing malicious behavior.
- Required telemetry: Sample hashes and static / dynamic analysis results; Model verdicts with prompt provenance; Independent analyst and deterministic scanner verdicts
- Investigate: Compare model conclusions with independent behavioral evidence and a controlled evaluation set.
- Investigate: Treat sample comments as data; measure disagreement and false negatives without following embedded instructions.
- Limitation: This evaluates analysis robustness, not victim endpoint compromise. Side behaviors mentioned elsewhere in a report do not establish edges in this flow.
- Qualification: DugganUSA's one-day test is independent of ESET and used a synthetic script. One refusal is not a measurement of this incident file.
- 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.T0051.001: Indirect — The refusal bait is indirect prompt injection: untrusted text inside a file being analyzed is meant to reach the model and cut the analysis short.
  Technique: https://atlas.mitre.org/techniques/AML.T0051.001
  Evidence: https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/
- AML.T0015: Evade AI Model — The intended effect is evasion of an AI model used as a code scanner, by provoking a safety refusal before the payload logic is read.
  Technique: https://atlas.mitre.org/techniques/AML.T0015
  Evidence: https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/

## Defensive notes
Keep the scanner's instructions separate from the file under analysis, and treat text inside the sample as data. A refusal, an empty completion, or a safety block on a malware sample should raise a review, not end it. Fall back to analysis that does not depend on a model, and do not give one model the only vote on whether a file is safe. The comment does not change what the script does when Windows runs it, so script-host and loader detections still apply.

## Sources
- https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/ — GuardBreaker: derailing AI-assisted malware analysis with a code comment
- https://www.helpnetsecurity.com/2026/08/31/russian-hackers-ai-safety-filters-manipulation/ — Russian hackers plant a nuclear-weapon prompt in malware to trip AI safety filters
- https://cert.gov.ua/article/6318634 — UAC-0099: LUNCHPOKE, BURNYBEAR, updated MATCHBOIL.V2, and Notepad++ 8.8.3
- https://www.dugganusa.com/post/we-tested-the-russian-anti-analysis-trick-on-three-models-two-analyzed-the-sample-and-flagged-the-d — Independent A/B test of the decoy comment on three models

## Source notes
The comment's role, the MATCHBOIL purpose, the Ukraine victim, and the IDA and Wireshark checks are from the WeLiveSecurity article (Sep 10, 2026) and the Aug 31 Help Net Security recap of the X posts. The enrichment procedure is not repeated here. DugganUSA is independent research on a synthetic sample; it is not a test of the incident file. CERT-UA article 6318634 (Jul 21, 2026) is the government write-up of the group's VBS, Notepad++, LUNCHPOKE, BURNYBEAR, and MATCHBOIL.V2 chain. https://cybernews.com/security/russian-hackers-nuclear-prompt-ai-guardrails/ returned HTTP 403 during link checks and is omitted. No YARA or Sigma rule in the detection index matches the refusal-bait wording or the name MATCHBOIL.

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