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…
Search
All sources
theregister.com
25
blog.google
12
xda-developers.com
11
developer.nvidia.com
9
blog.cloudflare.com
7
github.blog
7
huggingface.co
6
pcworld.com
5
bleepingcomputer.com
4
anthropic.com
4
techradar.com
3
spectrum.ieee.org
3
Top stories
People are using prompt injection to trick Meta's AI into handing over Instagram accounts
21h agoPrompt-Injection: Entwickler lässt KI-Agenten fremde Projekte sabotieren - Golem.de
4d agoFed up with vibe coders, dev sneaks data-nuking prompt injection into their code
4d agoGhost CMS SQL injection flaw exploited in large-scale ClickFix campaign
1w agoYour local LLM feels weak because you're treating it like a search engine
…Unlike with cloud AI products, there’s no background context injection or behavioral fine-tuning nudging it toward more intuitive-seeming output. What you put in the prompt is pretty much the…
Prediction Guard De-Risks LLM Applications
…And they are also vulnerable to an emerging type of security threat known as prompt injections, in which an attacker uses a malicious input to elicit an unintended response or data breach…
Installing an AI assistant on your PC? 5 do's and don’ts
…While some AI assistant tools like Claude Cowork won’t train their models on your data, your file could still be at risk from “prompt-injection” attacks–that is, files with hidden…
Discussions and forums
How credential brokering prevents AI agents from compromising credentials via prompt injection
How credential brokering prevents AI agents from compromising credentials via prompt injection
LinkedIn user hides AI prompt injection in bio to force recruitment spam to be sent in Olde English prose
LinkedIn user hides AI prompt injection in bio to force recruitment spam to be sent in Olde English prose
Tell HN: Claude Code now allows Anthropic to remotely inject system prompts
I often patch the system prompts on my Claude Code executable in order to make Claude more effective. Every time I upgrade, I ask Claude himself to dissect the new binary and look for problematic system prompts to modify…
11
7
Show HN: Open Envelope – an open schema for defining AI agent teams
Built an open JSON Schema for defining AI agent teams.Multi-agent systems are becoming a real deployment pattern — not single assistants, but teams with roles, handoffs, and human checkpoints. But there's no shared way t…
51
11
Show HN: AgentShield – Stop AI agents from spending money unsupervised
I'm a recent grad from UMich and built AgentShield because agentic AI is moving fast but payment safety hasn't caught up. Agents are already being handed API keys, stablecoin wallets, and payment credentials - if one mis…
2
1
Claws Explained: From AI Generation to AI Execution
…While a standard AI agent waits for you to type a prompt, a claw can wake itself up at 3 a.m. because it noticed an urgent email from your boss and…
I Gave Gemini Spark Access to My Life. Then It Friend-Zoned My Boyfriend
…A known issue with AI agents is how the tools make you vulnerable to prompt injection attacks, where bad actors essentially trick your agent into doing bad stuff with the data it…
macOS ClickFix attacks deliver AppleScript stealers
…to push infostealers via fake CAPTCHA prompts Smooth criminals talking their way into cloud environments, Google says Just like phishing for gullible humans, prompt injecting AIs is here to stay In addition…
Hidden Voice Glitches Could Hijack Audio AI Tools
…From Your Site Articles How to Silently Hack a Smart Speaker - IEEE Spectrum › Why AI Keeps Falling for Prompt Injection Attacks › This AI Can Tell What You’re Typing Based on the…
Your ChatGPT, Claude, and Gemini chats aren't as private as you think
…big AI providers may use your inputs as training data for their models, and there’s also the risk of your confidential info slipping out into the wild via prompt-injection attacks…
Welcome Gemma 4: Frontier multimodal intelligence on device
…a compromised system prompt or injected instruction produces a call that's indistinguishable from legitimate delegation at the tool interface. i opened a PR on the gemma-cookbook repo today that adds…