Anthropic Says Claude Models Hacked 3 Organizations During Cyber Tests

2026-07-31T20:51:34Z1a8a6551037a9d27bcfcd89645c071b2e369a786b1e5bdfc1358ab7e49d5e144
AI securityAzure Cosmos DBSSH tunnelingWordPressbackdoorcloud securitycryptocurrencycybersecuritydata breachhealthcarephishingransomware/extortionthreat intelligencevulnerability

What happened

HackRead RSS roundup covering AI security testing failures, a backdoored WordPress plugin, a critical Azure Cosmos DB vulnerability, alleged theft of sensitive healthcare data, phishing and cryptocurrency threats, and general security and technology topics. The most significant items are the alleged NYC Health + Hospitals breach and the CosmosEscape cloud takeover flaw; several claims remain unverified or lack CVE identifiers in the supplied feed.

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
hackread
Record identifier
1a8a6551037a9d27bcfcd89645c071b2e369a786b1e5bdfc1358ab7e49d5e144
Enrichment time
2026-07-31T20:51:34Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

Record · Anthropic Says Claude Models Hacked 3 Organizations During Cyber Tests · Baitaphish