Security

When you give an AI agent access to your tools, you've created a privileged insider. The threat model is different from a compromised service — because the agent acts non-deterministically, at scale, on your behalf.

Threat intelligence was built on the assumption that your analysis layer is neutral. LLMs trained on public CTI reports aren't neutral — they've absorbed adversarial narratives, attribution biases, and threat actor disinformation before you wrote a single query.

In 2002, SQL injection was a known attack that most developers dismissed as someone else's problem. By 2010 it was the top cause of data breaches. Prompt injection is at the 2002 stage. The trajectory is the same.

IAM roles, network policies, secrets rotation schedules — all designed for humans or static services. AI agents are neither. They're dynamic, non-deterministic actors with legitimate credentials, and your current policy model doesn't account for them.

Engineers spend hours getting secrets to work locally. Every out-of-date .env.example is lost velocity. Secrets aren't just a security concern — they're a developer experience bottleneck.

Every HTTP request you make likely passes through a proxy you never configured. Here is the network-level mechanism — iptables NAT REDIRECT, TPROXY, Squid in action, and why HTTPS only partially protects you.

Georgia Tech tracked 35 CVEs from AI-generated code in March 2026 alone — more than all of 2025 combined. Here's what the data says, why it's happening, and what a secure AI workflow actually looks like.