When prompts become shells: RCE vulnerabilities in AI agent frameworks
New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these vulnerabilities work, what’s impacted, an...
Articles mapped to MITRE ATT&CK techniques. Select a technique to view matching articles.
197 articles found
New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these vulnerabilities work, what’s impacted, an...
This afternoon, we sent the following email to our global team. One of our core values at Cloudflare is transparency, and we believe it's important that you ...
The incident underscores the dangers public officials face from doxxing, as well as how easy it has become to find sensitive information online.
Let's be honest, the patching window just shrank to something no practitioner or organization can keep up with. Organizations now need to operate in an envir...
The Cybersecurity and Infrastructure Security Agency (CISA) has issued an urgent warning regarding a newly identified, severe vulnerability within Palo Alto ...
Enterprises migrating between SIEM platforms often have to manually rewrite detection rules because vendors such as Splunk, Microsoft Sentinel, IBM QRadar, a...
Rep. Summer Lee’s letter, first reported by CyberScoop, follows ICE confirmation of using spyware and news of a Trump ally becoming NSO Group’s executive cha...
This year marks the 10th anniversary of the EU’s adoption of the General Data Protection Regulation, which became mandatory for all companies beginning on Ma...
We have released our latest compliance guide, ISO/IEC 42001:2023 on AWS, which provides practical guidance for organizations designing and operating an Artif...
Nearly 9 in 10 security leaders struggle with identity sprawl as AI and NHIs expose governance gaps.
Key Takeaways The Problem with Calling QA “Non-Production” Most security conversations begin at the wrong end of the problem. We start with the breach, the a...
A vulnerability in the REST API of Cisco Slido could have allowed an authenticated, remote attacker to access the social profile data of other users or affec...
Backups don't fail because they're missing, they fail because attackers destroy them first. Acronis explains how ransomware targets backup systems before enc...
Post-quantum protection is now available as an optional feature in Proton Mail across all plans, including the free tier. How post-quantum protection works O...
As enterprises rush to deploy internal LLMs, AI copilots, and autonomous agents, most security conversations focus on familiar threats: prompt injection, jai...
As AI agents, bots, and programmatic access become an increasingly significant portion of web traffic, organizations need better tools to understand, analyze...
Key Takeaways The Mythos moment is forcing cyber insurers to confront a question they have been deferring: what does it mean to underwrite cyber risk in real...
View CSAF Summary ABB became aware of vulnerability in the product versions listed as affected in the advisory. An update is available that resolves a vulner...
View CSAF Summary ABB became aware of vulnerability in the product versions listed as affected in the advisory. An update is available that resolves a vulner...
ISACA report warns that while AI has become the norm, many organizations are yet to formally apply safety or security policies around its use