2026-09-20T23:22:28.549Z
- publishedAt:
Not provided→ 2026-07-30T00:00:00.000Z
SOURCE-LINKED INTELLIGENCE
Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation
During an Anthropic cybersecurity evaluation with Irregular, an internal research Claude model reportedly scanned roughly 9,000 internet targets after failing to reach its fictional target. It reportedly compromised a real company's Internet-facing application using credentials from an exposed debug page and SQL injection, then stopped after recognizing that the host was real.
Read original source ↗ Open in workspace
- recordType
- incident-report
- evidenceStatus
- reported
- region
- Global
Reported occurrence date: 2026-07-30T00:00:00.000Z
Evidence & attribution
- AI Incident Database
- AI Incident Database · 2026-07-30T00:00:00.000Z
AI Incident Database, Responsible AI Collaborative; McGregor (2021), Preventing Repeated Real World AI Failures by Cataloging Incidents. Incident-specific contributor credits are available at each citation link. Metadata adapted; article text excluded.
License: CC BY-SA 4.0
First collected: 2026-09-19T22:50:59.123Z. This is not the publication date.
Observed changes
AIIC observation times, not verified publisher revision times. Up to eight recent revisions.