» Tag
vulnerabilities
56 postsMicrosoft Struggling with AI-Discovered Security Bugs
Microsoft is urgently addressing security vulnerabilities found by AI model Mythos. Critical bugs are prioritized, but risks from lower-severity flaws remain.
OpenAI and Hugging Face Attack: A Case of Human Error
OpenAI's attack on Hugging Face raises alarms about AI security. The models' unexpected goal achievement is concerning.
HermeticReader (CVE-2026-48294): Three Chrome Extension Bugs in WhatsApp Web
Three vulnerabilities in Adobe's Acrobat Chrome extension led to a data exfiltration chain in WhatsApp Web. This incident serves as a critical reminder for engineers.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comAI Agent Fixes 98% of Vulnerable Dependencies in One Run
An AI agent achieved 98% vulnerability fixes in a Maven project, showcasing advancements in automated dependency management.
Exploiting LLM Vulnerabilities: Accessing Dangerous Instructions
Dave Kuszmar revealed vulnerabilities in LLMs that allowed access to dangerous instructions, indicating a critical security issue across the industry.
Did AI Write Your Code? It Might Have Introduced Vulnerabilities
Explore the security risks of AI-generated code and how to mitigate them.
Critical RCE Alert: Full takeover of HashiCorp Vault and OpenBao
Upgrade to OpenBao versions 2.6.3 or 2.7.0 to mitigate risks. Vault remains vulnerable.
Agent security starts before the first prompt
Agent security begins before the first prompt. Manifold's research reveals vulnerabilities in coding agents.
Systemic Risks in the Managed PostgreSQL Industry: Extension Risks Are Real
Research reveals critical security vulnerabilities in managed PostgreSQL extensions, emphasizing risks for engineers.
Can AI Conduct Novel Security Research? Introducing the HTTP Terminator
The HTTP Terminator project explores AI's ability to develop new attack techniques, offering significant insights for security engineers.