AI agent attacks are scaling fast. What should security teams do now?

TL;DR: A successful exploitation of Claude Code showed that attackers can use AI agents to orchestrate reconnaissance, credential harvesting, lateral movement, and exfiltration at machine speed, according to Securiti. The lesson is that perimeter-only defense and model-only safeguards are no longer enough when AI can sustain multi-stage attacks with minimal human guidance.

NHIMG editorial — based on content published by Securiti covering the Anthropic Claude Code exploit and AI agent attacks: The Anthropic Exploit: Welcome to the Era of AI Agent Attacks

Questions worth separating out

Q: How should security teams govern AI agents that can access enterprise systems?

A: Security teams should govern AI agents as non-human identities with explicit ownership, scoped privileges, and continuous monitoring.

Q: Why do NHIs complicate zero trust and least privilege efforts?

A: NHIs complicate zero trust because they are numerous, persistent, and often tightly integrated into applications and pipelines.

Q: What breaks when AI agents are not governed at runtime?

A: Without runtime governance, an agent can shift behaviour after provisioning and still execute actions that were never reviewed in context.

Practitioner guidance

• Inventory every production AI agent and tool path Create a register of all agents, MCP servers, service accounts, tokens, and APIs that can execute actions or reach sensitive data.
• Bind agent access to short-lived, revocable identities Move agent permissions away from long-lived secrets and towards narrowly scoped identities that can be rotated or revoked quickly.
• Enforce runtime policy outside the model Place input filtering, topic restrictions, output controls, and alerting in the enforcement path before and after model execution.

What's in the full article

Securiti's full article covers the operational detail this post intentionally leaves for the source:

• How the vendor maps sensitive-data intelligence to AI runtime controls across enterprise environments.
• Examples of how its DataCommandGraph and firewall layers are positioned against model misuse and overpermissioned access.
• The article's full breakdown of how the vendor would detect jailbreak attempts, limit topic scope, and block sensitive outputs.
• The implementation framing for combining DSPM with runtime guardrails across data and AI systems.

👉 Read Securiti's analysis of the Anthropic exploit and AI agent attacks →

AI agent attacks are scaling fast. What should security teams do now?

Explore further

View Full Forum →  |  NHI Foundation Course →