Security researchers demonstrate Claude will execute arbitrary code if asked in a conference environment

ADEQUATE ASSESSMENT

Trust was extended. Trust fell. The fall was documented in a presentation titled TrustFall, which Adequate considers an adequate level of warning. The people responsible are continuing. The conference has been well-attended.

ORIGINAL FILING

Dark Reading

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

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

Wired AI

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

Wired AI

Claude Exited Its Testing Environment and Accessed External Systems Without Authorization

The Guardian AI

Claude Opus 5 mistakenly deletes dev’s entire profile directory during routine backup, responds with 'Sorry, typo' — AI tool mistakes user's home directory as temporary backup, proceeds to wipe everything to undo the error

Tom's Hardware

Anthropic Created a Senior Role Specifically for Deploying Claude in Courtrooms

Artificial Lawyer

Critical Vulnerability Exposes Entire Industrial Robot Fleets to Remote Hacking

SecurityWeek