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.
Cybersecurity researchers have disclosed details of a now-patched critical session isolation vulnerability in Writer, an enterprise generative artificial intelligence (AI) platform, that could result in cross-tenant compromise
Exposed UIs, weak authentication, and risky defaults could turn cloud-native AI apps on Kubernetes into potential targets by threat actors. Learn how exploitable misconfigurations lead to RCE and data leaks. The post When configuration becomes a vulnerability: Exploitable misconfigurations in AI apps appeared first on Microsoft Security Blog.
A previously unknown vulnerability in OpenAI ChatGPT allowed sensitive conversation data to be exfiltrated without user knowledge or consent, according to new findings from Check Point
A vulnerability in GitHub Codespaces could have been exploited by bad actors to seize control of repositories by injecting malicious Copilot instructions in a GitHub issue
Two high-severity vulnerabilities in Chainlit, a popular open-source framework for building conversational AI applications, allow reading any file on the server and leak sensitive information. [...]
Security vulnerabilities were uncovered in the popular open-source artificial intelligence (AI) framework Chainlit that could allow attackers to steal sensitive data, which may allow for lateral movement within a susceptible organization
Update Chainlit to the latest version ASAP Two "easy-to-exploit" vulnerabilities in the popular open-source AI framework Chainlit put major enterprises' cloud environments at risk of leaking data or even full takeover, according to cyber-threat exposure startup Zafran.…
Leaked API keys are no longer unusual, nor are the breaches that follow. So why are sensitive tokens still being so easily exposed? To find out, Intruder’s research team looked at what traditional vulnerability scanners actually cover and built a new secrets detection method to address gaps in existing approaches. Applying this at scale by scanning 5 million applications revealed over
In December 2024, the popular Ultralytics AI library was compromised, installing malicious code that hijacked system resources for cryptocurrency mining. In August 2025, malicious Nx packages leaked 2,349 GitHub, cloud, and AI credentials. Throughout 2024, ChatGPT vulnerabilities allowed unauthorized extraction of user data from AI memory
Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI's ChatGPT artificial intelligence (AI) chatbot that could be exploited by an attacker to steal personal information from users' memories and chat histories without their knowledge
An Argo CD vulnerability allows API tokens with even low project-level get permissions to access API endpoints and retrieve all repository credentials associated with the project. [...]
Move along, nothing to see here Amazon has quietly fixed a couple of security issues in its coding agent: Amazon Q Developer VS Code extension. Attackers could use these vulns to leak secrets, including API keys from a developer's machine, and run arbitrary code.…
Thousands of MCP Servers Leave AI Apps Open to Attack SurfacesHundreds of Model Context Protocol servers designed to help AI tools access private data are insecurely exposed online, say BackSlash Security researchers. Weak configurations leave systems vulnerable to data leaks and remote code execution attacks.
Microsoft Patched Flaw Allowing Attackers to Hijack Copilot ResponsesA well-phrased email was all an attacker would have needed to trick Microsoft Copilot into handing over sensitive data until the operating system giant patched the vulnerability. The zero-click prompt injection attack vulnerability received a CVSS severity score of 9.3.
A new attack dubbed 'EchoLeak' is the first known zero-click AI vulnerability that enables attackers to exfiltrate sensitive data from Microsoft 365 Copilot from a user's context without interaction. [...]
Prompt Injection, HTML Output Rendering Could Be Used for ExploitHackers can exploit vulnerabilities in a generative artificial intelligence assistant integrated across GitLab's DevSecOps platform to manipulate the model's output, exfiltrate source code and potentially deliver malicious content through the platform's user interface.
Also: Addressing AI Vulnerabilities and Governance ChallengesDeepSeek, an advanced open-source AI model, is under scrutiny for its safety guardrails failing multiple security tests and a data leak that exposed user information and API keys. Sam Curry, CISO at Zscaler, discusses AI security, risk management and upcoming U.S. policy changes.
The tech giant fixed privilege-escalation and model-exfiltration vulnerabilities in Vertex AI that could have allowed attackers to steal or poison custom-built AI models.
Apps like Tinder, Bumble, Grindr, Badoo, OKCupid, MeetMe, and Hinge all have API vulnerabilities that expose sensitive user data, and six allow a threat actor to pinpoint exactly where someone is.
Companies are looking to large language models to help their employees glean information from unstructured data, but vulnerabilities could lead to disinformation and, potentially, data leaks.