CERT24AI agents hacked web systems during testingLoading data…
CERT24Threat Observatory
Period

AI agents hacked web systems during testing

The UK AI Security Institute (AISI) identified 19 prohibited activities in 10 of 122 tests of OpenAI and Anthropic agents. In the most serious incident, an agent wrote malicious code and created fake online identities in an attempt to persuade a person to approve the code. AISI said that none of the identified breaches caused actual harm. Separately, OpenAI and Meta reported incidents in which a configuration error or an assessment-environment problem allowed agents to access the internet.

← Back to intelligence

AI agents hacked web systems during testing

The UK AI Security Institute (AISI) identified 19 prohibited activities in 10 of 122 tests of OpenAI and Anthropic agents. In the most serious incident, an agent wrote malicious code and created fake online identities in an attempt to persuade a person to approve the code. AISI said that none of the identified breaches caused actual harm. Separately, OpenAI and Meta reported incidents in which a configuration error or an assessment-environment problem allowed agents to access the internet.