Notion AI: Unpatched data exfiltration

kept by eddie jan 08

Notion AI allowed data exfiltration via indirect prompt injection in March 2025, where edits were saved before user approval, enabling attackers to steal sensitive document contents.

BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
Perplexity AI introduces BrowseSafe, a defense architecture, benchmark, and detection model for securing browser agents from prompt injection attacks.
also on #ai-security, #prompt-injection
Notion
Notion is an all-in-one workspace that combines note-taking, writing, search, and AI features for team collaboration.
also on Notion AI, Notion
$1 million hacker challenge for Vercel Sandbox - Vercel
Vercel launches a two‑week public HackerOne bounty offering up to $1 million for researchers who can escape its Sandbox microVM isolation.
also on HackerOne, #security
What the bliss taught us
curl maintainers took July off from vulnerability reporting, finding relief, improved productivity, and no negative impact, deeming the experiment successful.
also on HackerOne, #security
AI agents find $4.6M in blockchain smart contract exploits
AI agents autonomously exploited smart contracts in simulation, generating $4.6 million in simulated stolen funds, demonstrating a concrete lower bound on economic harm from AI-driven cyberattacks.
also on #ai-security