· ai-devtools

AI agent API security hasn't caught up with agents already running in production

A quarter of the organizations surveyed already have agents making calls to their APIs while running in production.


This finding emerged from a survey administered by Postman to nearly 9,000 developers, architects, and executives regarding their management of AI agents.

The responses reveal a common pattern: enterprises prioritized deploying the new technology before establishing clear protocols for access control.

The complexities surrounding who controls the necessary keys present a significant challenge.

Specifically, roughly four out of every ten respondents mentioned they have not yet figured out how to manage credentials and identity for these agents.

Related coverage

Also worth reading

  1. next.js 16.5.0-canary.59 released
  2. Bell Canada confirms agentic hacker stole enterprise customer data on November 17 2026
  3. Cyber leaders find clear communication a front-line defense capability
  4. Meta releases Triton TLX, a Native GPU Compiler Extension for advanced hardware control
  5. AI agents autonomously find and exploit 0-day in MONAI Label to take over university server