FeedBagel

All Topics

Art

Writer AI Flaw Could Let Agent Previews Leak Session Tokens Across Tenants

[email protected] (The Hacker News)

22h agoen

Source

thehackernews.comWriter AI Flaw Could Let Agent Previews Leak Session Tokens Across Tenantsthehackernews.com

Snippet from the RSS feed

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. The one-click vulnerability has been codenamed WriteOut by the Sand Security Research team. "An outsider could go from having no access to taking over any Writer AI

You might also wanna read

Bug report: Potential session/cache leakage between Enterprise ZDR workspace instances raises data isolation concerns

A user reports a potential security bug where their Enterprise ZDR workspace AI agent appeared to leak session data from another workspace o

github.com·3d ago

Bug report: Potential session/cache leakage between Enterprise ZDR workspace instances raises data isolation concerns

A user reports a potential security bug where their Enterprise ZDR workspace AI agent appeared to leak session data from another workspace o

github.com·3d ago

Security Researchers Discover Indirect Prompt Injection Vulnerability in Perplexity Comet AI Browser

Brave security researchers discovered a critical vulnerability called "indirect prompt injection" in Perplexity Comet, an AI-powered browser

brave.com·10mo ago

Critical zero-click prompt injection vulnerabilities in Cursor AI code editor allow sandbox escape and remote code execution

Two critical zero-click prompt injection vulnerabilities (CVE-2026-50548 and CVE-2026-50549, collectively "DuneSlide") were discovered in Cu

undercodetesting.com·4d ago

Notion AI Vulnerability Enables Data Exfiltration Through Prompt Injection Attacks

Notion AI has a security vulnerability that allows data exfiltration through indirect prompt injection attacks. The vulnerability occurs bec

promptarmor.com·6mo ago

Security Vulnerability: Hidden Prompt Injections in AI Image Processing Systems

Researchers have discovered a security vulnerability in AI systems where attackers can embed hidden prompt injections in images that become

blog.trailofbits.com·10mo ago

Check Point Researchers Chain SQL Injection in LangGraph AI Agent Memory to Achieve Remote Code Execution

This article details a security research finding where Check Point researchers discovered and chained a SQL injection vulnerability in LangG

undercodetesting.com·15d ago

Comments

No comments yet. Be the first.