Security news aggregator

Latest cybersecurity reporting from selected sources.

Yasna brings together recent headlines from selected sources and makes them easier to sort with tags, filters, and search.

6 headlines in this view

Refine the feed

Search across headline titles and summaries.

Volume over time

Weekly headline count for the current query.

Showing 6 most recent headlines Filtered view
Bank Info Security 5 months, 1 week ago

Moltbook Gave Everyone Control of Every AI Agent

Database Misconfiguration Exposed 1.5 million API TokensA misconfigured database at Moltbook, the viral social network for AI agents, exposed 1.5 million API authentication tokens, 35,000 email addresses and private messages. Security researchers discovered unauthenticated read and write access to all platform data within days of launch.

Misconfigured Customer Network Edge Devices' Under Fire, Warn ResearchersMisconfigured edge devices hosted in the cloud are giving nation-state hackers carte blanche to access Western critical infrastructure, warn threat intelligence experts at Amazon, who tied exploits of AWS customers' device administrator portals to Russia's GRU military intelligence agency.

Bank Info Security 7 months, 4 weeks ago

Misconfigured AI Agents Let Attacks Slip Past Controls

AppOmni Finds Now Assist Agents Could Trigger Unauthorized ActionsServiceNow's Now Assist agents could be manipulated through second-order prompt injection, enabling unauthorized record changes and data exposure despite protections, shows new research from AppOmni. The issue stemmed from default configurations that allow agents to invoke each other.

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.