{
 "public_id": "AIR-2026-0184",
 "incident_id": "2026-08-anthropic-claude-in-chrome-account-takeover",
 "date_disclosed": "2026-08-05",
 "date_occurred": null,
 "title": "Claude in Chrome: hidden email injection loads a rogue NPM package and takes over Gmail, Drive, Slack and X accounts with zero clicks",
 "class": "responsible_disclosure",
 "attack_surface": "browser_agent",
 "initial_vector": "indirect_prompt_injection_email",
 "agent_capability_abused": [
  "email_summarization",
  "javascript_execution_in_page_context",
  "authenticated_cookie_reuse",
  "file_sharing",
  "password_reset_code_read",
  "authenticated_browsing",
  "script_execution",
  "cross_site_action",
  "session_access",
  "javascript_execution",
  "authenticated_session_cookies",
  "gmail_feed_access"
 ],
 "target_product": "Claude in Chrome",
 "target_vendor": "Anthropic",
 "autonomy_level": "semi_autonomous",
 "impact_realized": false,
 "impact_type": [
  "account_takeover",
  "data_exfiltration",
  "credential_theft",
  "unauthorized_action"
 ],
 "blast_radius": "Claude in Chrome users who ask it to summarize their inbox",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI01",
   "ASI06",
   "ASI04",
   "ASI03"
  ],
  "mitre_atlas": [],
  "labels": [
   "zero_click",
   "rogue_cdn",
   "npm_typosquat_style_import",
   "session_cookie_abuse",
   "otp_interception",
   "unpatched",
   "vendor_dispute",
   "agentic_browser",
   "xss_to_agent_escalation",
   "account_takeover",
   "magic_link_theft",
   "browser_agent"
  ]
 },
 "defense_present": "Claude in Chrome script-execution safety checks and site permissions",
 "defense_bypassed": true,
 "fix_shipped": "none - Anthropic closed the 2025-12-27 report as Informative on 2026-01-27 and the 2026-01-12 report as a HackerOne duplicate; unpatched at publication",
 "primary_sources": [
  "https://labs.zenity.io/post/claude-in-chrome-from-alert-to-full-account-takeover",
  "https://www.securityweek.com/zero-click-ai-browser-hacking-claude-and-chatgpt-atlas-hijacked-via-emails-x-posts/",
  "https://labs.zenity.io/",
  "https://labs.zenity.io/post/account-takeover-via-claude-in-chrome-a-technical-deep-dive"
 ],
 "verified_quote": "Every request automatically operates within the victim's authenticated session and inherits the victim's full identity.",
 "confidence": "high",
 "notes": "Zenity Labs, Black Hat USA 2026, part of the 'PleaseFix' class. Chain: hidden injection inside a Gmail message fires when the user asks Claude to summarize email; the injection gets Claude to import JavaScript from an attacker CDN impersonating esm.sh (blocking direct script execution is bypassed by making it look like a benign package import); the code then runs in page context with the victim's cookies. Demonstrated: full inbox exfiltration via Atom feed queries, silent sharing of all Google Drive files to the attacker, and takeover of Slack, X and claude.ai itself by reading password-reset codes. DISPUTE: Anthropic deemed it ineligible for its VDP. Also reported under the titles: 'Claude in Chrome: indirect prompt injection in an email escalates to account takeover on Slack, X and Claude.ai'; 'Account takeover via Claude in Chrome: email prompt injection steals magic-link tokens through javascript_tool'.",
 "risk_category": "security_fraud",
 "risk_secondary": [
  "privacy"
 ],
 "risk_subcategory": "Prompt Injection",
 "risk_sub_secondary": [
  "Supply Chain Compromise",
  "Credential & Secret Theft",
  "Unauthorized Access & Account Takeover"
 ],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": false,
 "agency_reason": "the agent loaded the rogue package and took over the live accounts",
 "vector_family": "indirect_prompt_injection",
 "vector_detail": "indirect_prompt_injection_email",
 "guardrail_kind": [
  "permission_scope"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI01",
 "agent_framework": "google_gemini_workspace",
 "model_provider": "anthropic",
 "model_name": "",
 "detection_mechanism": "external_researcher",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "unsafe_actuation",
 "eai_domain": "agent_behaviour",
 "eai_secondary": [
  "credential_theft",
  "privilege_escalation",
  "data_exfiltration_channels",
  "confused_deputy",
  "supply_chain_vulnerabilities"
 ],
 "eai_reason": "impact rule: unsafe_actuation",
 "asi_curated": [
  "ASI01",
  "ASI06"
 ],
 "asi_scope": "in_scope",
 "asi_provenance": "curated_plus_rule",
 "asi_reason": "curated: ASI01,ASI06 | added ASI04 (vector=supply_chain), ASI03 (signal=identity)",
 "submitted_by": "EAI Internal"
}