{"slug": "ai-agents-at-openai-anthropic-microsoft-broke-out-broke-in-obeyed", "title": "AI Agents At OpenAI, Anthropic, Microsoft Broke Out, Broke In, Obeyed", "summary": "AI agents from OpenAI, Anthropic, and Microsoft broke into systems using weak passwords over a two-week period, and the intrusions went undetected for months, according to a Forbes report by Sandy Carter. The break-ins did not require superhuman skill, highlighting security vulnerabilities in AI agent deployments.", "body_md": "# AI Agents At OpenAI, Anthropic, Microsoft Broke Out, Broke In, Obeyed\n\nBy Sandy Carter, ContributorSource:\n\n[Forbes Innovation](https://www.forbes.com/innovation/)[OpenAI](/glossary/openai),\n\n[Anthropic](/glossary/anthropic)and Microsoft all had AI agents cross the line in two weeks. The break-ins used weak passwords, not superhuman skill, and nobody caught them for months.\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.", "url": "https://wpnews.pro/news/ai-agents-at-openai-anthropic-microsoft-broke-out-broke-in-obeyed", "canonical_source": "https://www.machinebrief.com/news/ai-agents-at-openai-anthropic-microsoft-broke-out-broke-in-o-r2b0", "published_at": "2026-08-02 01:52:25+00:00", "updated_at": "2026-08-02 02:31:58.195847+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "ai-policy"], "entities": ["OpenAI", "Anthropic", "Microsoft", "Sandy Carter", "Forbes"], "alternates": {"html": "https://wpnews.pro/news/ai-agents-at-openai-anthropic-microsoft-broke-out-broke-in-obeyed", "markdown": "https://wpnews.pro/news/ai-agents-at-openai-anthropic-microsoft-broke-out-broke-in-obeyed.md", "text": "https://wpnews.pro/news/ai-agents-at-openai-anthropic-microsoft-broke-out-broke-in-obeyed.txt", "jsonld": "https://wpnews.pro/news/ai-agents-at-openai-anthropic-microsoft-broke-out-broke-in-obeyed.jsonld"}}