CVE-2026-0153General(google / android)

LOWCVSS 7.8 · HIGH

Signal is active with 1 mentions in latest observed window

Immediate actions

  • Patch google android systems immediately

Recommended action window: Monitor and triage in normal cycle

NVD description

In Write of msg_to_host_buffer.cc, there is a possible out of bounds write due to an incorrect bounds check. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation.

0.5/ 10 priority

Sources & remediation

Weakness type (CWE)
CWE-787

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

AVAILABLE

Momentum

STABLE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

  • android

Threat summary

  • Patch or workaround signal is available
  • 2 mentions across 2 observed days
  • Momentum state: stable

What's happening

  • Patch or workaround mentioned in 1 signal
  • Technical details provided in 1 signal
  • General: 1 classified signal
  • Peaked 1d ago at 1 mentions (2026-07-29); latest day: 1
  • 2 total mentions across 2 days

Affected systems

Vendors
Products
android

1 version affected across 1 product

Deep dive

Activity timeline2 mentions / 2d
00111Mentions · 2026-07-29: 1Mentions · 2026-08-01: 1Patch / Workaround · 2026-08-01: 1Technical Details · 2026-08-01: 107-2908-01
Signal classification2 categories
General
150.0%
Patch
150.0%
Referenced assets1 URL
By indicator
Classification over time
DateTotalLabels
2026-07-291
General1
2026-08-011
Patch1
Full discourse2 posts
  • CertiK@CertiK
    General

    AI security is no longer just about protecting the model. CertiK researcher Guanxing Wen (@hhj4ck) identified two vulnerabilities in Google’s EdgeTPU (CVE-2026-0150 & CVE-2026-0153), acknowledged in Google’s June 2026 Security Bulletin. As AI agents gain access to sensitive systems, securing hardware, privilege boundaries, and infrastructure is becoming just as important as securing the model itself. Read more👇 https://www.certik.com/blog/certik-identifies-google-edgetpu-vulnerabilities

    Post summary

    CertiK researcher Guanxing Wen announced two EdgeTPU vulnerabilities (CVE‑2026‑0150 & CVE‑2026‑0153) acknowledged by Google in its June 2026 Security Bulletin, but offers no further technical details or evidence of exploitation.

    1712948.4K
    559.4K followersView on X
  • joecrypto@CertiKjoseph
    Patch

    【AIセキュリティの常識が変わる】 GoogleのAIチップ「EdgeTPU」に高リスクな脆弱性を発見 🚨 モデルを守るだけでは不十分?AIセキュリティは今、「ハードウェア」の領域へ——。 Web3・AIセキュリティのCertiKは、GoogleのオンデバイスAIチップ「EdgeTPU」で2件の深刻な脆弱性(CVE-2026-0150 / CVE-2026-0153)を特定しました。(※Google側も承認済み、2026年6月のセキュリティパッチにて修正完了) プロンプトインジェクションなど「AIモデル自体の攻撃」対策に注目が集まる中、今回の発見は「ハードウェアやインフラ層全体の保護」がいかに緊急の課題であるかを物語っています。 💡 ここがポイント ・何が起きた? 1. OS(オペレーティングシステム)とAIチップ間を繋ぐインターフェースが悪用され、セキュリティ保護をすり抜けてチップ上で不正コマンドが実行されたり、内部データを狙われたりするリスクを解明。 2. なぜ企業にとって重要なの? AIエージェントが決済や本人確認まで担う時代。「モデル単体」ではなく、「ハードウェア ➔ OS ➔ 外部ツール」というシステム全体の繋がりを狙う攻撃が増えています。 3. これからの対策は? モデル単体のチェックにとどまらず、開発の初期段階からシステム全体(フルスタック)でセキュリティを検証する姿勢が不可欠です。 詳細な分析やQ&AはCertiK公式ブログにて公開中👇 🔗 https://www.certik.com/blog/certik-identifies-google-edgetpu-vulnerabilities 技術的なご質問やご相談は、以下までお気軽にご連絡ください! 📩 joseph.hung@certik.com

    Post summary

    CertiK identified two high‑risk vulnerabilities (CVE‑2026‑0150 and CVE‑2026‑0153) in Google EdgeTPU hardware, with a security patch scheduled for release in June 2026.

    00040532
    1.4K followersView on X
CPE platform detail1 entries

1 of 1 entries

PartVendorProductVersionTarget SWTarget HW
OSgoogleandroid---

Explore more