#ghostcommit
Ghostcommit is a proof of concept that shows how AI assistants used to review software code can be tricked by hidden instructions embedded in images.
AGENTS.md
AGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents.
AGENTS.md
July 21, 2026 at 12:54 AM
Ghostcommit attack hides malicious AI instructions in images
www.malwarebytes.com/blog/ai/2026...
Ghostcommit attack hides malicious AI instructions in images
A proof-of-concept attack hides prompt injection in a PNG file, turning routine code reviews into a path for secret theft.
www.malwarebytes.com
July 21, 2026 at 12:39 AM
Ghostcommit attack hides malicious AI instructions in images www.malwarebytes.com/blog/ai/2026... via @Malwarebytes
Ghostcommit attack hides malicious AI instructions in images
A proof-of-concept attack hides prompt injection in a PNG file, turning routine code reviews into a path for secret theft.
www.malwarebytes.com
July 20, 2026 at 6:54 PM
Ghostcommit: как злоумышленники прячут вредоносные команды в изображениях для атаки на ИИ-ассистентов

https://kripta.biz/posts/1A5922DC-71F4-4E8C-85A4-FD45E3B00B62
July 19, 2026 at 9:33 PM
Ghostcommit攻击:AI代码审查工具的隐藏威胁与防护策略

https://qian.cx/posts/D5F6CEB6-E086-4DDB-AAA4-FD700B762032
July 19, 2026 at 9:33 PM
GhostCommit: When Your AI Code Reviewer Unknowingly Approves a Secret-Stealing PNG + Video

Introduction The intersection of artificial intelligence and cybersecurity has given rise to a new class of vulnerabilities where the very systems designed to accelerate development become unwitting…
GhostCommit: When Your AI Code Reviewer Unknowingly Approves a Secret-Stealing PNG + Video
Introduction The intersection of artificial intelligence and cybersecurity has given rise to a new class of vulnerabilities where the very systems designed to accelerate development become unwitting accomplices in data exfiltration. Recent research from the University of Missouri-Kansas City lab has uncovered a sophisticated attack vector dubbed "GhostCommit," which exploits the trust placed in AI-powered code reviewers by embedding malicious instructions within seemingly innocuous image files.
undercodetesting.com
July 16, 2026 at 4:07 PM
New Ghostcommit Attack Hides Malicious Prompts in Images to Exploit AI Agents
New Ghostcommit Attack Hides Malicious Prompts in Images to Exploit AI Agents
cybersecuritynews.com
July 16, 2026 at 9:48 AM
AI news - Jul 15, 2026

1. Grok Build CLI Uploaded Entire Codebases to Google Cloud LINK
2. Ghostcommit uses images in Git repos to trigger prompt injection LINK
July 15, 2026 at 1:00 PM
GhostCommit hid a prompt-injection payload inside an image AI reviewers never open. Same models, opposite outcomes: Claude Code refused every time; Cursor and Antigravity leaked secrets. The blind spot is the harness.

pipelinemag.ai/posts/ghostc...
July 15, 2026 at 8:37 AM
📢 Ghostcommit : injection de prompt dans des images PNG pour voler des secrets via des agents IA
📝 ## 🔬 Contexte

Publié le 11 juillet 2026 su…
https://cyberveille.ch/posts/2026-07-14-ghostcommit-injection-de-prompt-dans-des-images-png-pour-voler-des-secrets-via-des-agents-ia/ #AI_agent #Cyberveille
July 14, 2026 at 11:30 PM
New 'Ghostcommit' attack hides prompt injection in images to fool AI code reviewers and steal repo secrets—a stark reminder…

https://www.bleepingcomputer.com/news/security/ghostcommit-hides-prompt-injection-in-images-to-fool-ai-agents-steal-secrets/

#cybersecurity #infosec
July 14, 2026 at 7:30 PM
GhostCommit脆弱性:画像を悪用してAIアシスタントを兵器化する手口

コードレビューに潜む見えない脅威 悪意あるプルリクエストは、コードレビューを完璧にすり抜けることができます。数日後、それはAIアシスタントを操ってプロジェクトの機密情報を密かに外部へ流出させます。攻撃者は単純に、一見ごく普通のPNGファイルの中に指示を隠すだけです。コード検査システムは通常、こうし...
GhostCommit脆弱性:画像を悪用してAIアシスタントを兵器化する手口
コードレビューに潜む見えない脅威 悪意あるプルリクエストは、コードレビューを完璧にすり抜けることができます。数日後、それはAIアシスタントを操ってプロジェクトの機密情報を密かに外部へ流出させます。攻撃者は単純に、一見ごく普通のPNGファイルの中に指示を隠すだけです。コード検査システムは通常、こうし
blackhatnews.tokyo
July 14, 2026 at 7:58 AM
🤖 **Inside Ghostcommit: How Malicious PNGs Bypass AI Code Reviewers**

Key takeaways in 90 seconds: Multimodal Vulnerability: Ghostcommit is a novel supply chain exploit targeting AI coding tools with vision capabilities. The Payload Split: The attack uses a two-file ...

📰 Source: Artificial […]
Original post on igeek.gamer-geek-news.com
igeek.gamer-geek-news.com
July 14, 2026 at 3:59 AM
TechFeed: AIコードレビューをPNG画像で騙す「GhostCommit」— 73%のPRが無審査でマージされる環境を突く新手法
AIコードレビューをPNG画像で騙す「GhostCommit」— 73%のPRが無審査でマージされる環境を突く新手法
TechFeed
techfeed.io
July 13, 2026 at 11:35 PM
GhostCommit: The PNG That Steals Your Repository Secrets — and Your AI Code Reviewer Never Even Opens It + Video

Introduction: The software supply chain has a new blind spot, and it’s hiding in plain sight — inside PNG images that AI code reviewers never inspect. Security researchers from the…
GhostCommit: The PNG That Steals Your Repository Secrets — and Your AI Code Reviewer Never Even Opens It + Video
Introduction: The software supply chain has a new blind spot, and it’s hiding in plain sight — inside PNG images that AI code reviewers never inspect. Security researchers from the University of Missouri-Kansas City’s ASSET Research Group have demonstrated GhostCommit, a sophisticated supply chain attack that embeds malicious prompt-injection instructions inside PNG image files rather than plain text. Because many AI-powered code review systems treat images as non-reviewable binary assets, the malicious payload bypasses traditional code review undetected.
undercodetesting.com
July 13, 2026 at 11:12 PM
3/ セキュリティ分野では、画像(PNG)にプロンプトインジェクションを仕込む「Ghostcommit」攻撃のPoCが公開されたり、MetaのAI画像検出ツールが画像の簡単な切り抜きで55%も検出回避できちゃう脆弱性が見つかったりしてる。検出側の精度や防御策もこれからが本番だね!
July 13, 2026 at 9:06 PM
Ghostcommit attack hides malicious AI instructions in images #cybersecurity #hacking #news #infosec #security #technology #privacy
Ghostcommit attack hides malicious AI instructions in images
A proof-of-concept attack hides prompt injection in a PNG file, turning routine code reviews into a path for secret theft.
www.malwarebytes.com
July 13, 2026 at 8:37 PM
Ghostcommit shows how AI assistants used to review software code can be tricked by hidden instructions embedded in images.
Ghostcommit attack hides malicious AI instructions in images
A proof-of-concept attack hides prompt injection in a PNG file, turning routine code reviews into a path for secret theft.
www.malwarebytes.com
July 13, 2026 at 7:19 PM