Background:
When leveraging agentic and non-agentic AI capabilities, especially when your solution is connected to your database, your organization can face another threat besides prompt injection: [...] Read more
Background:
Prompt injection is one of the most well-known attacks against LLMs. The primary goal of a threat actor in such attacks is to extract secrets and other sensitive data from the environment [...] Read more
Background:
Because industry started leveraging AI capabilities for routine cases like general customer support, a new threat has emerged: data poisoning. Core attack category:
Based on MITRE ATLAS, [...] Read more
Background:
Only looking into well-known attack patterns found in Chrome and other browser extensions is not enough. Since we work daily with IDEs, there is another potential attacker [...] Read more
Background:
During the incident response analysis stage, it is mandatory to answer the question of how the attacker appeared inside the environment. This becomes especially challenging when dealing [...] Read more
Background:
Sometimes during daily cases we see suspicious detections on Linux machines which have hashes that do not exist on popular platforms and we do not have licenses for sandboxes. To resolve [...] Read more
Background:
A few days ago, there was a notification about a memory leak issue (CVE) affecting MongoDB. Shortly after, a proof-of-concept (POC) was released on one of the version control channels. As [...] Read more
Background:
As AI technologies rapidly advance, it is essential for us as cybersecurity specialists to understand how we can defend against emerging threats. One scenario that comes to mind is the [...] Read more
Background:
Some XDR and EDR solutions are not effective when dealing with threats hidden inside WSL. In certain cases, it can also be challenging for digital forensic specialists to detect threats [...] Read more
Background:
Recently, some unknown specialists uploaded several dumps from servers that, according to their claims, are related to Kimsuky (State sponsored) systems. As cybersecurity defenders, we [...] Read more
