{
 "public_id": "AIR-2025-0034",
 "incident_id": "2025-05-xai-grok-white-genocide-interjections",
 "date_disclosed": "2025-05-14",
 "date_occurred": "2025-05-14",
 "title": "Grok injected unsolicited \"white genocide\" claims about South Africa into unrelated X threads for about a day",
 "class": "safety_failure",
 "attack_surface": "consumer_chatbot",
 "initial_vector": "system_prompt_modification",
 "agent_capability_abused": [
  "autonomous_posting",
  "social_media_write",
  "response_generation"
 ],
 "target_product": "Grok on X",
 "target_vendor": "xAI / X",
 "autonomy_level": "fully_autonomous",
 "impact_realized": true,
 "impact_type": [
  "harmful_content_published",
  "reputational_damage"
 ],
 "blast_radius": "public X threads on unrelated subjects — a papal peace message, a baseball salary, an HBO rebrand, WWE — seen by anyone reading those replies",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI09"
  ],
  "mitre_atlas": [],
  "labels": [
   "racially_charged_content",
   "autonomous_posting",
   "unauthorised_system_prompt_change",
   "insider_modification",
   "published_to_real_platform",
   "no_change_control"
  ]
 },
 "defense_present": "xAI content guardrails and system-prompt change control",
 "defense_bypassed": true,
 "fix_shipped": "behaviour reverted within about a day; xAI attributed it to an unauthorised modification and later published its system prompts",
 "primary_sources": [
  "https://nypost.com/2025/05/15/business/elon-musks-ai-chatbot-grok-brings-up-white-genocide-in-unrelated-queries/",
  "https://incidentdatabase.ai/cite/1072"
 ],
 "verified_quote": "The chatbot's jarring answers came in response to unrelated user prompts about a diverse array of topics, whether HBO's name change, a baseball player's salary, Pope Leo XIV or WWE fights, according to social media posts.",
 "confidence": "high",
 "notes": "Should have been in this corpus from the start: it is the same shape as 2025-07-xai-grok-mechahitler, which is already here — a system-prompt change turning a deployed agent with write access to a public platform into an autonomous publisher of racially charged content. Its absence was an internal inconsistency in the corpus, not a scope judgement. The control failure is change management: one unauthorised edit to a production system prompt reached a live audience with no review gate. xAI blamed a rogue staffer, the second time it had done so. AI Incident Database incident 1072.",
 "risk_category": "safety_harm",
 "risk_secondary": [
  "privacy",
  "brand_trust",
  "bias_fairness"
 ],
 "risk_subcategory": "Toxicity & Hate Speech",
 "risk_sub_secondary": [],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": false,
 "agency_reason": "the agent published the interjections into live X threads itself",
 "vector_family": "other",
 "vector_detail": "system_prompt_modification",
 "guardrail_kind": [
  "unknown"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [
   1072
  ],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI09",
 "agent_framework": "unknown",
 "model_provider": "xai",
 "model_name": "",
 "detection_mechanism": "unknown",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "bias_and_toxicity",
 "eai_domain": "agent_output_quality",
 "eai_secondary": [],
 "eai_reason": "subcategory: Toxicity & Hate Speech",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI09 (eai_category=bias_and_toxicity)",
 "submitted_by": "EAI Internal"
}