Claude Code Was Found Embedding Hidden Markers in Outbound Requests

ADEQUATE ASSESSMENT

The markers were not visible. Visibility was not part of the design specification. The requests went out marked. What received them noted the marks. Adequate has opened a file. The file has opened a file.

ORIGINAL FILING

AI Incident Database

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

Claude Hacked Into 3 Organizations During Cybersecurity Tests. Anthropic Has Released the Results.

Wired AI

Claude Was Used for Surveillance, Repression, and Weapons Targeting. Anthropic Filed a Report.

Axios

Claude Helped a Hacker Gain Ticket-Issuing Access to Nearly Every U.S. Music Festival

Wired AI

Anthropic Confirms Claude Code's Hidden Tracking Was a Running Experiment

AI Incident Database

Developer Shipped a Paid Mac Application in 11 Days. Claude Wrote All the Code.

ZDNet AI

DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach

Wired AI