AI agent API security hasn’t caught up with agents already running in production A Postman survey of nearly 9,000 developers, architects and executives found that a quarter of responding organizations already run AI agents calling their APIs in production, while about four in ten respondents have not worked out how credentials and identity are managed for those agents. The findings, reported by Help Net Security, indicate that agent API security practices lag behind production deployments. Postman asked nearly 9,000 developers, architects and executives how they’re handling AI agents, and the answers tell a familiar story. Companies put the new thing to work first and left the question of who holds the keys for later. A quarter of the organizations that answered already have agents calling their APIs in production. Source: Postman The keys are where it gets uncomfortable. About four in ten respondents haven’t worked out how credentials and identity … More https://www.helpnetsecurity.com/2026/11/20/ai-agent-api-security-production/ The post AI agent API security hasn’t caught up with agents already running in production https://www.helpnetsecurity.com/2026/11/20/ai-agent-api-security-production/ appeared first on Help Net Security https://www.helpnetsecurity.com .