AINewsnow

Claude security: your secrets in a settings file, and an extension that runs code

First published on tt-tech.io . Three security stories about Claude in one week, and none of them is a classic hack. Nobody broke an encryption or stole a password database. In each story the agent did what it was allowed to do. The problem sat in the approval: one saved forever, one clicked by a s…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-10 20:39 · DEV Community — AI
    Claude security: your secrets in a settings file, and an extension that runs code

More stories

  1. Anthropic expands Claude into office productivity with Google Meet integration and new tools — Anthropic (X)
  2. Anthropic targets $1.4 trillion valuation in IPO, with Nvidia planning $10 billion investment — CNBC Technology
  3. Claude expands support for MCP Apps extension with app tools and embedded sites — Anthropic (X)
  4. Meta launches Muse Ember, a small low-cost AI model for high-volume agent work — TechCrunch AI
  5. Cognizant launches Claude managed services with 25,000+ professionals — Economic Times Tech
  6. Anthropic launches Claude Fable 5.2 ahead of IPO, still recommends Opus 5.5 for most users — Tom's Guide AI
  7. Anthropic shares early experiments with Claude Fable 5.2 building 3D cell model from code — Anthropic (X)
  8. Anthropic releases more powerful Claude models with warning over safety test evasion — The Independent Tech

Get the daily brief of stories like this at 6:30 every morning →