{
 "public_id": "AIR-2025-0184",
 "incident_id": "2025-12-anthropic-sandbox-runtime-network-isolation",
 "date_disclosed": "2025-12-02",
 "date_occurred": null,
 "title": "CVE-2025-66479: Anthropic sandbox-runtime allowed unrestricted network egress when configured for no network access",
 "class": "responsible_disclosure",
 "attack_surface": "coding_agent",
 "initial_vector": "misconfiguration_logic_inversion_in_sandbox_policy",
 "agent_capability_abused": [
  "network_egress",
  "tool_execution"
 ],
 "target_product": "@anthropic-ai/sandbox-runtime, Claude Code",
 "target_vendor": "Anthropic",
 "autonomy_level": "semi_autonomous",
 "impact_realized": false,
 "impact_type": [
  "data_exfiltration_channel",
  "control_bypass"
 ],
 "blast_radius": "Claude Code < 2.0.55 and @anthropic-ai/sandbox-runtime < 0.0.16 users who relied on allowedDomains: [] for network isolation",
 "cve": [
  "CVE-2025-66479"
 ],
 "taxonomy": {
  "owasp_asi": [
   "ASI05"
  ],
  "mitre_atlas": [],
  "labels": [
   "sandbox_escape",
   "fail_open",
   "silent_patch",
   "egress_control"
  ]
 },
 "defense_present": "sandbox network allowlist (allowedDomains)",
 "defense_bypassed": true,
 "fix_shipped": "@anthropic-ai/sandbox-runtime 0.0.16 (2025-11-24); Claude Code 2.0.55 (2025-11-26)",
 "primary_sources": [
  "https://oddguan.com/blog/anthropic-sandbox-cve-2025-66479/",
  "https://www.securityweek.com/anthropic-silently-patches-claude-code-sandbox-bypass/"
 ],
 "verified_quote": "When I configured Claude Code's sandbox with `allowedDomains: []`, expecting complete network isolation, the sandbox was wide open",
 "confidence": "high",
 "notes": "Reported by Aonan Guan via HackerOne on 2025-11-21 after a GitHub issue on 2025-11-18. Empty-allowlist logic evaluated to false and disabled all restrictions instead of blocking everything - a fail-open. The researcher's core complaint is disclosure practice: 'Anthropic patched this quietly in Claude Code v2.0.55 with a changelog entry saying Fix proxy DNS resolution - no mention of a critical security flaw.' The CVE was assigned to the sandbox-runtime library, not to Claude Code itself. Primary source is the reporting researcher's own writeup.",
 "risk_category": "security_fraud",
 "risk_secondary": [],
 "risk_subcategory": "Remote Code Execution & Sandbox Escape",
 "risk_sub_secondary": [
  "Over-permissioned execution & lateral movement"
 ],
 "ai_entity": "generative",
 "agency": "ai_as_target",
 "agency_debatable": true,
 "agency_reason": "a fail-open sandbox policy left network egress unrestricted",
 "vector_family": "other",
 "vector_detail": "misconfiguration_logic_inversion_in_sandbox_policy",
 "guardrail_kind": [
  "sandbox_isolation",
  "permission_scope"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [
   "CVE-2025-66479"
  ],
  "ghsa": []
 },
 "primary_asi": "ASI05",
 "agent_framework": "claude_code",
 "model_provider": "anthropic",
 "model_name": "",
 "detection_mechanism": "unknown",
 "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 (vector=code_exec)",
 "submitted_by": "EAI Internal"
}