#prompt-injection

Articles tagged with #prompt-injection

One Email Was Enough: When a Guardrail Detects the Attack and Still Can't Stop It
Summary Salt Labs, the research arm of Salt Security, turned the agentic AI platform Manus into a path to remote code execution with a single email. The victim did not have to click a link, download a
Oct 13, 20269 min read
Agent Data Injection: Fooling AI Agents With the Data They Already Trust
Risk Summary You ask a web agent to summarize the reviews on a product page. A fake review planted by an attacker makes it click "Buy Now" instead, and an order goes through. No malware, no phishing,
Aug 6, 202620 min read8
Agent Data Injection: khi AI agent bị đánh lừa bằng chính dữ liệu nó tin tưởng
Tóm tắt rủi ro Bạn bảo một web agent: "tóm tắt giúp tôi các review trên trang này". Một review giả do kẻ tấn công đăng lên khiến agent bấm nhầm nút "Buy Now", và đơn hàng được đặt. Không malware, khôn
Jul 28, 202625 min read13
Ghostcommit: Hiding Prompt Injection Inside PNG Images to Trick AI Agents Into Stealing a Repository's Secrets
Overview On July 11, 2026, Ghostcommit — an attack technique published as a Proof-of-Concept by the ASSET Research Group (University of Missouri-Kansas City), led by Associate Professor Sudipta Chatto
Jul 14, 202614 min read5
Gemini's Secret Affair: Notification-Based Prompt Injection and the Fake Context Alignment Technique
A single WhatsApp message from an unknown number is enough to turn the Gemini voice assistant into an attacker's tool — opening the smart windows in a victim's home, live-streaming their video over Zo
Jun 23, 202612 min read20
Gemini's Secret Affair: Prompt injection gián tiếp qua notification và kỹ thuật Fake Context Alignment
Một tin nhắn WhatsApp từ số lạ là đủ để biến trợ lý giọng nói Gemini thành công cụ của kẻ tấn công: mở cửa sổ thông minh trong nhà nạn nhân, phát video trực tiếp qua Zoom, hay đọc tin nhắn riêng tư mỗ
Jun 16, 202614 min read12