# Anthropic Says Attackers Are Running Operations on Agent Frameworks, Not Just Asking for Help

Its September threat report describes a Russia-linked espionage campaign that used Claude to automate reconnaissance and rebuild tooling after detection against more than 20 organizations.

- Published: 2026-09-19T06:16:00.678Z
- Canonical: https://polylog.news/ai/2026-09-19/anthropic-says-attackers-are-running-operations-on-agent-fra
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Anthropic](https://www.anthropic.com/threat-intelligence-report-september-2026), [Unite.AI](https://www.unite.ai/anthropic-details-disrupted-claude-misuse-across-seven-harm-areas/), [Anthropic (report PDF)](https://www-cdn.anthropic.com/e50be2e51e7695dc4b1366a37a245a597377d3b5/Anthropic-Detecting-and-countering-091026.pdf)

Anthropic's threat intelligence report covers eight months of disrupted misuse, from December 2025 through August 2026, across seven harm categories including cyber operations, influence operations, surveillance, fraud, biological misuse, c…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-19/anthropic-says-attackers-are-running-operations-on-agent-fra (subscription information: https://polylog.news/pricing).