If we are talking about the model itself and not the app, these are open-weight PyTorch models. So unless there’s a backdoor in Hugging Face or the PyTorch runtime, there’s really no way for them to be malicious afaik.
SECURITY
-
Designing and Defending Effective, Reliable, Secure AI Agents
By
–
Oct 29, 11 AM ET – Join @CohenShuki (
@AI21Labs ) and @BarelTayouri (
http://
Mend.io) to explore how to design and defend effective, reliable, and secure AI agents. Register: https://
webinars.techstronglearning.com/designing-and-
defending-ai-agents-a-practical-guide?utm_campaign=23146601-2025.10.29-Mend.io-SB&utm_source=mend&utm_medium=mend-website
… -
Balancing AI Tool Safety with Practical Usefulness via MCP
By
–
Re: lethal trifecta, I think the best way there is to curate tools where you trust both the author and the potential space of responses. (we do that via MCP gateway implementations) 100% protecting against the lethal trifecta often puts too many limits and reduces the usefulness
-
Security Safeguards for AI Systems Like Locks
By
–
I do agree that it's not a 100% fool-proof solution, but I feel like we should at least have some safe-guards: the analogy I'd use is that many locks can be picked (with enough effort/time), but that doesn't mean we should stop using locks completely.
-
Signal’s Open Source Approach to Secure Communications
By
–
Hi!Personally, I’m not a fan of vibes-based trust. First VERIFY, then trust, is my motto. Which is why Signal is open source. We want everyone to be able to inspect our code, and our encryption protocol, and see for themselves the lengths we go to to protect your comms and
-
Signal Down: AWS Outage Affects Messaging Platform
By
–
PSA: we are aware that Signal is down for some people. This appears to be related to a major AWS outage. Stand by.
-
Louvre lacks AI cameras for priceless jewelry surveillance in 2025
By
–
HONTEUX En 2025, il n’y a pas au Louvre de caméras dotées d’Intelligence Artificielle pour surveiller des bijoux historiques inestimables L’archaïsme de l’Etat fait peur Les caméras dotées d’IA coûtent moins cher que les surveillants humains et sont plus efficaces
-
Defending Against MSS Threats: Cybersecurity Education and Best Practices
By
–
What can individuals do to push back on the MSS? Some ideas: – Educate yourself and others about MSS tactics, especially social engineering and cyber threats. – Use secure communication tools, practice good cyber hygiene, and avoid suspicious contacts online. Teach others how
-
North Korean Hackers Hide Malware Using Blockchain Technology
By
–
North Korean hackers just used the #Blockchain to hide malware — the first time ever seen. https://
thehackernews.com/2025/10/north-
korean-hackers-use-etherhiding-to.html
… https://
search.app/MxyDx #NorthKorea #Malware #infosecurity #CyberSecurity @SpirosMargaris @PawlowskiMario @mvollmer1 @gvalan @ipfconline1 @LaurentAlaus @Shi4Tech -
AI Search Agents Vulnerable to Malicious Website Manipulation
By
–
How safe are AI search agents when browsing the real, messy internet? A new study reveals that LLM-powered search agents are highly vulnerable to being misguided by unreliable or malicious websites. To test this, researchers developed SafeSearch, an automated red-teaming