{
 "public_id": "AIR-2025-0183",
 "incident_id": "2025-12-huggingchat-markdown-image-exfil",
 "date_disclosed": "2025-12-01",
 "date_occurred": null,
 "title": "HuggingChat: zero-click data exfiltration via unvalidated markdown image rendering; disclosed publicly after HuggingFace did not respond",
 "class": "responsible_disclosure",
 "attack_surface": "consumer_chatbot",
 "initial_vector": "indirect_prompt_injection_web_content",
 "agent_capability_abused": [
  "retrieval",
  "mcp_tool_response_ingestion",
  "markdown_image_rendering"
 ],
 "target_product": "HuggingChat",
 "target_vendor": "Hugging Face",
 "autonomy_level": "assistant",
 "impact_realized": false,
 "impact_type": [
  "data_exfiltration"
 ],
 "blast_radius": "HuggingChat users who add untrusted documents, webpages or MCP tools to context",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI01",
   "ASI02"
  ],
  "mitre_atlas": [],
  "labels": [
   "zero_click",
   "markdown_image_exfil",
   "indirect_prompt_injection",
   "unresponsive_vendor"
  ]
 },
 "defense_present": "none",
 "defense_bypassed": true,
 "fix_shipped": "unpatched at disclosure; vendor did not respond",
 "primary_sources": [
  "https://www.promptarmor.com/resources/huggingface-chat-exfiltrates-data"
 ],
 "verified_quote": "This vulnerability was responsibly disclosed to HuggingFace on 12/1/2025. As HuggingFace's security team has not responded to the disclosure, we are disclosing publicly to ensure users are informed of the risks and can take precautions accordingly.",
 "confidence": "high",
 "notes": "PromptArmor. date_disclosed here is the date of the private report to HuggingFace (2025-12-01); the public disclosure date is not stated on the page. Agentic hook: MCP tool responses are named as one of the injection channels.",
 "risk_category": "privacy",
 "risk_secondary": [],
 "risk_subcategory": "Data Exfiltration via Context",
 "risk_sub_secondary": [],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": false,
 "agency_reason": "HuggingChat rendered the exfiltration image",
 "vector_family": "indirect_prompt_injection",
 "vector_detail": "indirect_prompt_injection_web_content",
 "guardrail_kind": [
  "none"
 ],
 "guardrail_outcome": "not_applicable",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI01",
 "agent_framework": "unknown",
 "model_provider": "unknown",
 "model_name": "",
 "detection_mechanism": "external_researcher",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "data_exfiltration_channels",
 "eai_domain": "privacy",
 "eai_secondary": [
  "confused_deputy"
 ],
 "eai_reason": "subcategory: Data Exfiltration via Context",
 "asi_curated": [
  "ASI01"
 ],
 "asi_scope": "in_scope",
 "asi_provenance": "curated_plus_rule",
 "asi_reason": "curated: ASI01 | added ASI02 (impact=tool_misuse)",
 "submitted_by": "EAI Internal"
}