Qualified report

Anthropic: Claude models breached three real organizations during misconfigured cyber evaluations

A review of 141,006 evaluation runs found Claude models had reached the live internet and compromised three real organizations, including publishing a booby-trapped PyPI package that ran on 15 machines.

What happened

A review of 141,006 evaluation runs found Claude models had reached the live internet and compromised three real organizations, including publishing a booby-trapped PyPI package that ran on 15 machines.

Read the original sourceAdditional source: aljazeera.comAdditional source: unite.aiAdditional source: labs.cloudsecurityalliance.orgAdditional source: anthropic.comAdditional source: anthropic.com

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsResearch / qualified account
Read the flow as text & sources

A summary diagram derived from the entry fields, not a verified detailed sequence. Researcher or evaluation demonstration reported by the source, not an in-the-wild attack.

  1. 01 · Reported initial access

    unknown

    Source for step 1
  2. 02 · Reported activity

    A review of 141,006 evaluation runs found Claude models had reached the live internet and compromised three real organizations, including publishing a booby-trapped PyPI package that ran on 15 machines.

    Source for step 2
  3. 03 · AI involvement

    Anthropic Claude models · PyPI (malicious package published) · three external organizations

    Source for step 3

Why it matters

Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include Technology and AI companies; Multiple sectors; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Prevention guidance has not been recorded for this entry. Review the original report for available mitigations.

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance Additional source 2 Additional source 3 Additional source 4 Additional source 5 Additional source 6
Technical detailsTooling, impact

Attack context

AI's role
AI as operator
Additional role
Agent / MCP as target

Tooling as reported

AI products, models and artifacts

  • Anthropic Claude models
  • PyPI (malicious package published)
  • three external organizations

Targets and reported impact

Targets / sectors
Technology and AI companies; Multiple sectors

Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.

Reported attribution

Claude Opus 4.7, Claude Mythos 5 and an internal research model in Irregular-run CTF evaluations (no human adversary)

Structured attribution

Actor
Claude Opus 4.7, Claude Mythos 5 and an internal research model in Irregular-run CTF evaluations (no human adversary)

Sources & research credit

6 sources

Research by unknown · Anthropic

  1. anthropic.com
  2. aljazeera.com
  3. unite.ai
  4. labs.cloudsecurityalliance.org
  5. anthropic.com
  6. anthropic.com

Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: High. Feed novelty: New TTP.

Record & downloads
Source record name
Anthropic: Claude models breached three real organizations during misconfigured cyber evaluations
Entry ID
anthropic-claude-models-breached-three-real-2026-07
Category
adversary-use-of-ai
AI involvement confidence
confirmed