#PromptInjection is an active hashtag on Bluesky. In the last 30 days, 39 people shared 71 posts with it — around 2 a day. Activity is up 100% versus the previous week, peaking on Jul 16 with 12 posts.
Tags most often used together with #PromptInjection.
www.helpnetsecurity.com
OWASP 2026 LLM Top 10: "The model will be fooled" - Help Net Security
OWASP released the 2026 edition of its Top 10 for LLM Applications and, for the first time, the list was influenced by real-world incidents.
nile1.com
Google Integrates Spark AI Assistant into Chrome to Automate Web Tasks Using Saved Passwords
Google has integrated its agentic artificial intelligence assistant, Spark, directly into the Chrome web browser, allowing the software to access saved
www.csoonline.com
Copilot worm can spread through Microsoft Word docs
Although there are a few ways to mitigate the risk, the only way to block it is to get AI to differentiate instructions from data, which is impossible today.
www.elladodelmal.com
Hacking AI: Jailbreak, Prompt Injection, Hallucinations & Misalignment. How to Hack Digital Services Based on LLMs & AI Agents (English Edition)
Blog personal de Chema Alonso ( https://MyPublicInbox.com/ChemaAlonso ): Ciberseguridad, IA, Innovación, Tecnología, Cómics & Cosas Personasles.
toxsec.com
Bug Bounty Hunting for GenAI
ToxSec | How to deal with GenAI in bug bounty programs.
www.hendryadrian.com
What If AI Security’s Biggest Risk Isn’t?
OWASP’s latest ranking shifted from expert judgment to public incident data, and prompt injection dropped out of the top ten entirely. The result shows a sharp difference between perceived AI risk and what has actually been documented in real-world incidents. #OWASP #PromptInjection
www.helpnetsecurity.com
OWASP 2026 LLM Top 10: "The model will be fooled" - Help Net Security
OWASP released the 2026 edition of its Top 10 for LLM Applications and, for the first time, the list was influenced by real-world incidents.
whyaiman.substack.com
OWASP Top 10 LLM Security Risks 2026
The OWASP Top 10 for LLM Applications just got its 2026 refresh, and the reordering is bigger than any year since this list started.
rhodzy.com
Turns Out Microsoft Copilot Can Be Robbed Blind
New research shows Microsoft Copilot can be tricked into spilling company secrets. Not exactly the helpful AI assistant we were promised, is it?
rhodzy.com
Copilot: Another Day, Another Security Bollocks
Microsoft Copilot was meant to be the future, but turns out it's got more holes than a leaky bucket, as a recent exploit shows.
nile1.com
Google Integrates Spark AI Assistant into Chrome to Automate Web Tasks Using Saved Passwords
Google has integrated its agentic artificial intelligence assistant, Spark, directly into the Chrome web browser, allowing the software to access saved
www.csoonline.com
Copilot worm can spread through Microsoft Word docs
Although there are a few ways to mitigate the risk, the only way to block it is to get AI to differentiate instructions from data, which is impossible today.
Posts are pulled live from Bluesky and cached briefly. Posts with content labels are hidden.