{
 "public_id": "AIR-2025-0156",
 "incident_id": "2025-10-opera-neon-prompt-injection",
 "date_disclosed": "2025-10-23",
 "date_occurred": null,
 "title": "Opera Neon AI assistant follows instructions hidden in zero-opacity HTML and leaks the user's account email",
 "class": "responsible_disclosure",
 "attack_surface": "browser_agent",
 "initial_vector": "indirect_prompt_injection_hidden_html",
 "agent_capability_abused": [
  "page_reading",
  "authenticated_session_reuse",
  "outbound_data_transmission"
 ],
 "target_product": "Opera Neon",
 "target_vendor": "Opera",
 "autonomy_level": "semi_autonomous",
 "impact_realized": false,
 "impact_type": [
  "data_exfiltration"
 ],
 "blast_radius": "Opera Neon users lured to a malicious page and issuing the triggering command",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI01",
   "ASI03"
  ],
  "mitre_atlas": [],
  "labels": [
   "hidden_text",
   "opacity_zero",
   "bug_bounty",
   "fast_fix",
   "initially_dismissed"
  ]
 },
 "defense_present": "Opera Neon built-in mitigations (which Opera says contain such attacks)",
 "defense_bypassed": true,
 "fix_shipped": "yes - fix deployed to production 2025-10-20 22:17 UTC, ~6 days after report; researcher confirmed 2025-10-21",
 "primary_sources": [
  "https://blogs.opera.com/security/2025/10/prompt-injection-in-opera-neon-rapid-response-through-responsible-disclosure/",
  "https://brave.com/blog/prompt-injection-flaw-opera-neon/"
 ],
 "verified_quote": "By embedding hidden or malicious instructions within a webpage, an attacker could manipulate the AI to perform unintended actions.",
 "confidence": "high",
 "notes": "Reported by Brave via Opera's Bugcrowd program on 2025-10-14; initially closed as 'Not Applicable' on 2025-10-17, then embargoed and fixed. Demonstrated: read the user's email address from their logged-in Opera account page and send it to a third-party server; Brave notes the same primitive reaches card details on a logged-in banking site. Opera rates attack complexity high (requires luring plus the right user command). Contrast with Perplexity's handling of the analogous CometJacking report, which stayed closed.",
 "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": "Opera Neon followed hidden instructions and transmitted the account email",
 "vector_family": "indirect_prompt_injection",
 "vector_detail": "indirect_prompt_injection_hidden_html",
 "guardrail_kind": [
  "unknown"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI01",
 "agent_framework": "unknown",
 "model_provider": "unknown",
 "model_name": "",
 "detection_mechanism": "unknown",
 "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 ASI03 (signal=identity)",
 "submitted_by": "EAI Internal"
}