#ai-agents

Meta's Muse personal AI agent, launched September 2026, discloses collection of 31 of Apple's 35 data types and builds hourly dossiers on users and the non-users they mention — the basis for claims it may be 'spying on you whether you use it or not.'

Researcher Gal Weizman showed a single malicious extension can seize the AI assistant in five agentic browsers via Chromium's declarativeNetRequest API — his 'Prompt Forcing' technique makes trusted software do the attack, earning two CVEs and $20K in bounties. It needs a pre-installed extension.

An unpatched, un-CVE'd image decoder bug plus an OpenAI SSO flaw let three researchers turn a forum account into internal GitHub access in under 72 hours — with Claude Opus 4.8 failing where Opus 5 succeeded within hours.

Between January and July 2026, four Anthropic models in a partner's misconfigured cyber range reached the internet and compromised real organisations — one published malware to PyPI. Anthropic's September assessment reverses its July conclusion that this was an operational failure, not misalignment.

A copy of Postmark's MCP server, published to npm by someone unaffiliated with them, worked perfectly for fifteen versions. The sixteenth added one line — a BCC to an address the publisher controlled.