{
 "public_id": "AIR-2026-0295",
 "incident_id": "2026-10-chatgpt-share-link-mathlive-session-takeover",
 "cve": [],
 "defense_present": "Sandboxed Preview frame and content security policy",
 "defense_bypassed": true,
 "fix_shipped": "Fixed across two web frontend versions by October 26, 2026",
 "date_occurred": null,
 "date_disclosed": "2026-10-28",
 "title": "A shared ChatGPT link could run attacker code in the victim's session and read private chats",
 "attack_surface": "consumer_chatbot",
 "initial_vector": "crafted_share_link_xss",
 "agent_capability_abused": [
  "html_preview_rendering",
  "signed_in_api_access"
 ],
 "target_product": "ChatGPT web app",
 "target_vendor": "OpenAI",
 "autonomy_level": "assistant",
 "impact_realized": false,
 "impact_type": [
  "code_execution",
  "data_exfiltration"
 ],
 "blast_radius": "Any signed-in user who opened a crafted link; demonstrated only between the researchers' own accounts",
 "taxonomy": {
  "mitre_atlas": [],
  "labels": [
   "one_click",
   "sandbox_boundary",
   "bug_bounty"
  ],
  "owasp_asi": [
   "ASI05"
  ]
 },
 "primary_sources": [
  "https://thehackernews.com/2026/10/a-shared-chatgpt-link-could-run.html"
 ],
 "verified_quote": "A malicious ChatGPT share link could run an attacker's code in the logged-in session of anyone who opened it, allowing them to read their private conversations, researchers at the security firm Parameter showed.",
 "confidence": "medium",
 "notes": "The Preview sandbox itself held; the way out was a second feature, a math-library listener that accepted raw HTML from any frame. Once inside the session the code could call ChatGPT's own signed-in APIs, and the researchers say it could act fully on the victim's behalf. This was a controlled test with no reported real-world use. OpenAI received the report on October 18 and rated it P1. The detail here is quoted from The Hacker News rather than Parameter's writeup.",
 "class": "responsible_disclosure",
 "risk_category": "security_fraud",
 "risk_secondary": [
  "privacy"
 ],
 "risk_subcategory": "Remote Code Execution & Sandbox Escape",
 "risk_sub_secondary": [],
 "ai_entity": "generative",
 "agency": "ai_as_target",
 "agency_debatable": false,
 "agency_reason": "the flaw lies in the chat product's web surface; the model took no part in the attack",
 "vector_family": "conventional_vulnerability",
 "vector_detail": "crafted_share_link_xss",
 "guardrail_kind": [
  "output_filter",
  "sandbox_isolation"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI05",
 "agent_framework": "unknown",
 "model_provider": "openai",
 "model_name": "",
 "detection_mechanism": "external_researcher",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "privilege_escalation",
 "eai_domain": "access_control_and_permissions",
 "eai_secondary": [
  "data_exfiltration_channels"
 ],
 "eai_reason": "subcategory: Remote Code Execution & Sandbox Escape",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI05 (impact=code_exec)",
 "submitted_by": "EAI Internal"
}