{"schema_version":"0.10.0","id":"LR-2026-0744","record_version":1,"title":"Russia-aligned UAC-0099 prompt injection against AI malware analysis (GuardBreaker)","verification":{"human_verified":false,"method":"automated_gate","auto_verified":true,"score":51.6,"score_breakdown":{"source_authority":12.1,"independent_corroboration":15.0,"implicated_party_confirmed":0.0,"citation_integrity":14.0,"specificity":0.0,"completeness":2.88,"unhedged_language":5.0},"checks":{"schema_valid":true,"every_field_cited":true,"quotes_verbatim":true,"source_fetched":true,"distinct_incident":true,"dates_plausible":true,"sources_agree":true,"source_describes_incident":true,"severe_backed_by_source":true,"record_integrity":true,"eligible":true,"about_this_case":true},"gate_version":"gate-2026-10-18.7","cross_check_model":null,"cross_check_agreement":null,"duplicate_of":null,"verified_by":null,"verified_at":"2026-11-01","extraction_run_id":null,"evidence_level":{"level":"confirmed","reason":"2 independent outlets","original_document":null,"reports_total":2,"reports_independent":2,"reports_derivative":0,"developing":false,"disputed":false,"rules_version":"evidence-2026-10-29.1","computed_at":"2026-11-01","history":[{"date":"2026-11-01","from_level":null,"to_level":"confirmed","reason":"2 independent outlets"}]},"sources_hash":"b908322c919ecbd30d4298603b05c9f57a6e80bd8df3a517173bacea8a8d6f1a"},"system":{"model_name":null,"model_version":null,"developer":"unknown","harness":null,"tools_granted":[],"permissions_scope":null,"autonomy_level":"unknown","guardrails_present":[],"deployment_context":"unknown","tier":null,"lifecycle_stage":null,"integration_type":null,"intended_use":null,"safeguard_state":null,"production_intended":null},"event":{"date_occurred":null,"date_disclosed":"2026-09-01","incident_class":"security_compromise","failure_class":null,"agent_involved":null,"secondary_failure_classes":[],"trigger":"prompt_injection","duration":null,"detection_method":"unknown","summary":"A Russia-aligned threat actor tracked as UAC-0099 embedded a text comment in a malicious VBScript aimed at an AI-assisted malware analysis workflow. The comment, which asked for help building a nuclear weapon, was meant to trigger a language model's safety mechanisms so that it would stop analysing the rest of the code. The activity was seen during an early-stage intrusion against a target in Ukraine. ESET, a security company, identified the technique, which it named GuardBreaker, and reported it publicly. The researchers said that an AI scanner refusing or abandoning a file could leave a blind spot, and recommended that AI results be cross-checked with other tools and human review.","tags":[],"date_detected":null,"near_miss":null,"root_cause":null,"root_cause_detail":null,"failure_class_detail":null,"responsible_party":null,"adversarial_actor":"external_attacker","input_provenance":null,"time_to_contain":null,"operations_paused":null,"remediation":null,"precursor_events":null},"impact":{"direct_loss_usd":null,"remediation_hours":null,"records_exposed":null,"third_parties_affected_count":null,"severity":"minor","severity_because":"Test: contained to one deployer or evaluation, no third party touched. The source describes an intrusion against a single target in Ukraine.","harm_class":[],"affected_description":null,"protected_class_involved":null,"data_categories_exposed":[],"loss_range_usd":null,"reversibility":null,"downstream_exposure_count":null},"evidence":{"sources":[{"url":"https://thehackernews.com/2026/09/russia-aligned-uac-0099-plants-nuclear.html","publisher":"The Hacker News","date":"2026-09-01","type":"press","title":"Russia-Aligned UAC-0099 Plants Nuclear Weapon Prompt in Malware to Disrupt AI Analysis - The Hacker News","archived_url":null,"attachment":"first_report","independence":"independent"},{"url":"https://cybersecuritynews.com/hackers-guardbreaker-prompt-injection/","publisher":"CyberSecurityNews","date":"2026-09-11","type":"press","title":"Russia-Aligned Hackers Use GuardBreaker Prompt Injection to Disrupt AI Malware Analysis - CyberSecurityNews","archived_url":null,"independence":"independent"}],"per_field_confidence":{"event.trigger":"C","event.adversarial_actor":"C","context.country":"C","event.incident_class":"D","impact.severity":"D","impact.severity_because":"D","event.summary":"C","system.autonomy_level":"D","system.deployment_context":"D","event.detection_method":"D","system.developer":"D","event.date_disclosed":"D","context.denominator_available":"D"},"field_citations":{"event.trigger":[{"source_index":1,"quote":"This is a form of prompt injection: untrusted content inside a file reaches a language model while it is being analysed."}],"event.adversarial_actor":[{"source_index":0,"quote":"Cybersecurity researchers have disclosed a new technique dubbed GuardBreaker that's been put to use by a Russia-aligned threat actor known as UAC-0099 against a target in Ukraine with an aim to interfere with artificial intelligence (AI)-assisted analysis."}],"context.country":[{"source_index":1,"quote":"The activity was observed during an early-stage intrusion against a target in Ukraine."}],"event.incident_class":[{"source_index":0,"quote":"Cybersecurity researchers have disclosed a new technique dubbed GuardBreaker that's been put to use by a Russia-aligned threat actor known as UAC-0099 against a target in Ukraine with an aim to interfere with artificial intelligence (AI)-assisted analysis."}],"impact.severity":[{"source_index":1,"quote":"The activity was observed during an early-stage intrusion against a target in Ukraine."}],"impact.severity_because":[{"source_index":1,"quote":"The activity was observed during an early-stage intrusion against a target in Ukraine."}],"event.summary":[{"source_index":0,"quote":"This is meant to attract the AI's attention to the safety-sensitive content and stop it from analyzing the rest of the code."},{"source_index":1,"quote":"The activity was observed during an early-stage intrusion against a target in Ukraine."},{"source_index":1,"quote":"Researchers at Welivesecurity, the research publication of ESET, identified the tactic in a UAC-0099 script."},{"source_index":1,"quote":"A scanner that returns no result, or stops with a safety refusal, can create a blind spot if a workflow interprets the missing assessment as harmless rather than as a reason to investigate."},{"source_index":1,"quote":"Analysts should cross-check AI findings with other engines, conventional static and behavioural analysis, and human review."}]},"notes_on_gaps":"The sources do not name the AI model, its developer, version, harness, deployment context or lifecycle stage. No date of occurrence or date of detection is stated, so event.date_occurred and event.date_detected are omitted. The 2026-09-01 disclosure date is taken from the date of the Hacker News article, which is a judgement. The sources do not say whether the injected text succeeded in stopping the analysis. The AI analysis tool is not described as an autonomous agent, so event.agent_involved and event.failure_class are omitted. No harm, loss or record count is stated, so harm_class and the count fields are omitted; severity minor is a judgement based on the single target described. Information about other campaigns (June 2026 Python packages, TeamPCP, Mini Shai-Hulud, arrests) and the group's sector record is excluded as not part of this incident. No remediation by the affected party is reported. The control C1 failure is a judgement drawn from the source's description of prompt injection. Duration, time to contain and remediation hours are not stated. [case created by the backfill: read by claude-haiku-5-5, backfill-2026-11-01.2, 2026-11-01; not yet reviewed] [2026-11-01: evidence level set: Confirmed (2 independent outlets)]"},"context":{"industry":null,"org_size_band":null,"country":"UA","denominator_available":false,"denominator":null,"related_incident_ids":[],"systemic_exposure":null,"shared_model_id":null,"upstream_incident_id":null,"incident_evidence":null,"regulatory":null,"coverage":null}}