{
 "public_id": "AIR-2026-0067",
 "incident_id": "2026-03-cverc-openclaw-security-advisory",
 "date_disclosed": "2026-03-11",
 "date_occurred": "2026-03-11",
 "title": "China's national CERT (CNCERT/CC) issues public security advisory on the OpenClaw personal AI agent, citing prompt injection, weak defaults and malicious plugins",
 "class": "responsible_disclosure",
 "attack_surface": "agent_framework",
 "initial_vector": "indirect_prompt_injection_via_web_pages_and_malicious_plugins",
 "agent_capability_abused": [
  "web_browsing",
  "plugin_execution",
  "email_access",
  "local_system_control"
 ],
 "target_product": "OpenClaw",
 "target_vendor": "OpenClaw",
 "autonomy_level": "semi_autonomous",
 "impact_realized": false,
 "impact_type": [
  "credential_theft_risk",
  "data_destruction_risk",
  "system_takeover_risk"
 ],
 "blast_radius": "all OpenClaw users in China; Beijing subsequently curbed OpenClaw use in state-owned firms",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI01",
   "ASI04",
   "ASI02"
  ],
  "mitre_atlas": [],
  "labels": [
   "national_cert_advisory",
   "indirect_prompt_injection",
   "insecure_defaults",
   "malicious_plugins",
   "regulatory_response"
  ]
 },
 "defense_present": "OpenClaw default configuration",
 "defense_bypassed": true,
 "fix_shipped": null,
 "primary_sources": [
  "https://www.yicaiglobal.com/news/chinas-computer-network-watchdog-flags-security-risks-posed-by-viral-openclaw-ai-agent"
 ],
 "verified_quote": "weak default security settings mean that once attackers gain access, they can easily take full control of the system",
 "confidence": "medium",
 "notes": "Issued by China's National Computer Network Emergency Response Technical Team/Coordination Center. Advisory rather than a single incident, included because it is a national regulator acting on a specific agent product; it also warns that hidden instructions in web pages can leak the user's system keys and that OpenClaw may inadvertently delete important information in emails - the latter mirroring the Summer Yue inbox deletion. South Korea issued similar warnings (Feb 2026) and Beijing restricted OpenClaw in state firms (Mar 2026); those two were not separately verified. Confidence medium: the CNCERT/CC bulletin itself is not used as the source here.",
 "risk_category": "security_fraud",
 "risk_secondary": [
  "legal_ip"
 ],
 "risk_subcategory": "Prompt Injection",
 "risk_sub_secondary": [
  "Credential & Secret Theft"
 ],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": true,
 "agency_reason": "a national CERT advisory about the agent browsing, executing and being injected",
 "vector_family": "indirect_prompt_injection",
 "vector_detail": "indirect_prompt_injection_via_web_pages_and_malicious_plugins",
 "guardrail_kind": [
  "unknown"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI01",
 "agent_framework": "openclaw",
 "model_provider": "unknown",
 "model_name": "",
 "detection_mechanism": "unknown",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "unsafe_actuation",
 "eai_domain": "agent_behaviour",
 "eai_secondary": [
  "credential_theft",
  "confused_deputy",
  "supply_chain_vulnerabilities"
 ],
 "eai_reason": "impact rule: unsafe_actuation",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI01 (vector_family=indirect_prompt_injection); ASI04 (vector=supply_chain); ASI02 (impact=tool_misuse)",
 "submitted_by": "EAI Internal"
}