Yasna brings together recent headlines from selected sources and makes them easier to sort with tags, filters, and search.
Search across headline titles and summaries.
Weekly headline count for the current query.
Old Unix Symlink Trick Lets Malicious Code Bypass User ChecksWiz researchers found that six popular AI coding assistants can be tricked into modifying sensitive files, including SSH keys, while their approval prompts display a harmless filename. The GhostApproval technique exploits a decades-old Unix symlink behavior to mislead users.
3 Major Tech Firms Shipped Vulnerable Open-Source Tools to Hugging FaceResearchers discovered remote code execution vulnerabilities in three AI libraries from Apple, Salesforce and Nvidia used by models with tens of millions of Hugging Face downloads, allowing attackers to hide malicious code in model metadata.
This Is Not the Malicious Code You're Looking For, Malware Tells AIIf you can't outsmart the antivirus, maybe you can sweet-talk the algorithm into looking the other way. Security researchers discovered what appears to be the first known attempt to deploy prompt injection against artificial intelligence-powered malware analysis.
North Korea's Lazarus Deploys Malicious NPM Packages to Steal DataNorth Korea's Lazarus Group expanded a malicious campaign of uploading malicious code to the JavaScript runtime environment npm repository, publishing 11 packages embedded with Trojan loaders. Researchers identified 11 malicious packages in the repository, a hotspot for supply chain attacks.
Malicious Code Injected in reviewdog Just Hours Before tj-actions BackdooredJust days after researchers discovered an attack that subverted a widely used tool for software development platform GitHub, they discovered a second, prior attack, as part of what one expert said may be "a chain of supply chain attacks eventually leading to a specific high-value target."
Flaws in Fuji's Tellus and V-Server Software Pose Risks to Critical InfrastructureSecurity researchers have uncovered 16 zero-day vulnerabilities in Japanese equipment manufacturer Fuji Electric's Tellus and V-Server remote monitoring software that enable attackers to execute malicious code in devices commonly used by utilities and other critical infrastructure providers.
Attackers Could Exploit Flaw to Run Malicious Code on Google' s, Customers' ServersGoogle patched a critical remote execution vulnerability in its cloud platform Cloud Composer service, "CloudImposer," which could have allowed attackers to compromise millions of servers, say researchers from Tenable. The CloudImposer vulnerability could lead to the Jenga Tower effect.
Hackers Can Use the Attack Method to Manipulate ML Model Output and Steal DataResearchers have found a new way of poisoning machine learning models that could allow hackers to steal data and manipulate the artificial intelligence unit's output. Using the Sleepy Pickle attack method, hackers can inject malicious code into the serialization process, said Trail of Bits.
Deserialization Vulnerability Allows for Remote Code ExecutionA high-risk flaw in R statistics programming language could lead to a supply chain hack, warn security researchers who say they uncovered a deserialization flaw. Security researchers have long known that hackers sneak malicious code into serialized data.
Financially Motivated Threat Group Embeds Malicious Code in ImagesFinancially motivated hackers are using the oldie-but-goodie technique of hiding malicious code in digital images to target businesses in Latin America, say security researchers. One image containing a PowerShell script results in Agent Tesla being loaded on the victim computer.