Keeping Google Play & Android app ecosystems safe in 2025
…It was last updated on March 31, 2026.JanuaryWe terminated 40 Yo… By Trust & Safety May 08, 2026 Security AI threats in the wild: The current state of prompt injections on the…
Search
All sources
theregister.com
16
blog.google
9
anthropic.com
7
developer.nvidia.com
6
xda-developers.com
6
huggingface.co
5
blog.cloudflare.com
5
github.blog
4
pcworld.com
4
bleepingcomputer.com
3
spectrum.ieee.org
3
intel.com
3
Application security Archives
…a talented security researcher — @xiridium! Latest Safeguarding VS Code against prompt injections When a chat conversation is poisoned by indirect prompt injection, it can result in the exposure of GitHub tokens, confidential…
Architecting Security for Agentic Capabilities in Chrome
…While the agent is active, it checks every page it sees for indirect prompt injection. This is in addition to Chrome’s real-time scanning with Safe Browsing and on-device AI…
KnowledgeDeliver flaw exploited as a zero-day to install web shells
…Max-severity flaw in ChromaDB for AI apps allows server hijacking Ivanti warns of new EPMM flaw exploited in zero-day attacks Ivanti fixes EPMM zero-days chained in code execution attacks…
Top stories
Paper page - One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
…Rather than exposing a harmful objective in a single prompt, increasingly capable attackers can distribute their intent across multiple benign-looking turns. Recent studies show that even modern commercial models with advanced…
Documentation can contain malicious instructions for agents
…No warnings." None of this is particularly surprising given that it's simply a variation on the unsolved risk of AI models – indirect prompt injection . When AI models process content, they cannot…
Updating Classifier Evasion for Vision Language Models | NVIDIA Technical Blog
…some kind of prompt injection to override the system instruction, but in this scenario, we can only control the image while the text is fixed. Pixel perturbations When attacking traditional image classification…
Discussions and forums
Taming the Wild West of ML: Practical Model Signing with Sigstore
…Model and data poisoning , prompt injection , prompt leaking and prompt evasion are just a few of the risks that have recently been in the news. Garnering less attention are the risks around…
AI agents found vulns in this Linux and Unix print server
…of devices AI has gotten good at finding bugs, not so good at swatting them AI bug reports went from junk to legit overnight, says Linux kernel czar Claude attacks were 'Rorschach…
Announcing the AI Gateway Working Group
…AI Inference Security Guard against malicious prompts and prompt injection attacks. Content filtering for AI responses. Signature-based detection and anomaly detection for AI traffic. AI Inference Optimization Semantic routing based on…