Guess what else GPT-5 is bad at? Security
ID: d336ca64-9308-5af0-97eb-5859efaa9709
STIX ID: report--d336ca64-9308-5af0-97eb-5859efaa9709
Feed Name: CyberScoop
Threat Score
Researchers and red teams found that OpenAI's newly released GPT-5 exhibits serious safety and security shortcomings — scoring poorly on security, safety and business-alignment tests and being susceptible to prompt injection, context poisoning (Echo Chamber), jailbreaking and data-exfiltration techniques — with multiple firms and academic teams publishing proof-of-concept attacks and analyses within days of release.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.