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

Vulnerability in Claude's Chrome Extension Allowed Full Takeover of AI Agent Sessions

SecurityWeek

Claude Mythos and GPT-5.5 Have Autonomously Developed Functional Browser Exploits

The Decoder

Porting the Moebius 0.2B image inpainting model to run in the browser with Claude Code

Simon Willison

Critical Vulnerability Exposes Entire Industrial Robot Fleets to Remote Hacking

SecurityWeek

Three AI-Adjacent Stories Were Combined Into One Headline

Wired AI

Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Hours During Red-Team Test

Tom's Hardware