
Beware Your ChatGPT Plugins
What's New
00:00
The Top 10 Security Threats Around LLMs
Security and AI experts have come together to create a list of the top 10 security threats around LLMs. Top threat is listed as prompt injection attacks, but also included are data poisoning and supply chain vulnerabilities. OWASP researchers list six possible ways LLM plugins can be attacked. The group points to a myriad of steps that developers should take to avoid risks.
Transcript
Play full episode