# What Anthropic reported about AI-assisted espionage

> Anthropic's November 2025 report describes a campaign using Claude Code and explains the limits of its findings.

Source: https://fullbytedeveloper.com/blog/anthropic-ai-espionage-report-context
Originally posted: 2025-12-13
Published here: 2026-11-06

Anthropic reported in November 2025 that attackers had used Claude Code in an espionage campaign detected that September. The company attributed the operation to a Chinese state-sponsored group with high confidence and said it targeted roughly thirty organizations, succeeding in a small number of cases. These are Anthropic's investigation findings. [1]

## Automation still had human direction

The report describes attackers using an agent's tools to carry out work, rather than only asking it for advice. Its description of extensive automation does not mean the campaign had no human operators. Attribution and the extent of automation should remain attached to the reporting organization. [1]

## Review what an agent can reach

For a legitimate development workflow, inventory the credentials, repositories and network destinations available to each agent. Give it the access needed for the task and retain logs of its actions.

Treat unfamiliar instructions in external content as untrusted input. Review consequential actions before execution, particularly when they expose data or change access.

The defensive lesson is to examine the agent's permissions and actions alongside the quality of its text output.

## Sources

1. [Anthropic espionage investigation](https://www.anthropic.com/news/disrupting-AI-espionage)

## Original posts

- [Instagram post](https://www.instagram.com/fullbytedeveloper/p/DSNGaNOkhtb/)