Security · 2h ago
Researcher Finds High-Severity AI Security Flaw in Khan Academy's VDP
A security researcher discovered a high-severity vulnerability in Khan Academy's AI features through its vulnerability disclosure program. The flaw could allow prompt injection attacks, potentially compromising AI responses. Khan Academy has acknowledged the issue and is working on a fix.
Meridian48 take
The finding highlights the growing attack surface of AI-integrated educational platforms, where prompt injection remains an underappreciated risk.
Read the full reporting
How I Found a HIGH-Severity AI Security Issue on Khan Academy's VDP →
DEV Community
ai-securityprompt-injection