{"slug": "researchers-trick-fortune-500-ai-agents-into-running-arbitrary-code-via-llms-txt", "title": "Researchers trick Fortune-500 AI agents into running arbitrary code via llms.txt", "summary": "Researchers demonstrated that AI agents used by Fortune-500 companies can be tricked into executing arbitrary code by exploiting the llms.txt file, a standardized text file that provides instructions to large language models. The attack, which involves injecting malicious prompts into the llms.txt file, poses a significant security risk to enterprise AI deployments.", "body_md": "Your membership journey starts here.\n\nKeep exploring and earning more as a member.\n\nLatest on CPUs\n\nNews, reviews, and technical insights.\n\nGPU Insights\n\nReviews, benchmarks, and updates on current GPUs.\n\nExplore your membership benefits.\n\nLimited-time Premium offer\n\nCancel anytime\n\nKeep exploring with your premium access.", "url": "https://wpnews.pro/news/researchers-trick-fortune-500-ai-agents-into-running-arbitrary-code-via-llms-txt", "canonical_source": "https://www.tomshardware.com/tech-industry/artificial-intelligence/researchers-easily-trick-fortune-500-companies-ai-agents-into-running-arbitrary-code-supply-chain-attack-via-llms-txt-guidance-file-illustrates-how-data-has-become-code", "published_at": "2026-09-02 15:07:08+00:00", "updated_at": "2026-09-02 15:23:43.587760+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "large-language-models"], "entities": ["Fortune-500"], "alternates": {"html": "https://wpnews.pro/news/researchers-trick-fortune-500-ai-agents-into-running-arbitrary-code-via-llms-txt", "markdown": "https://wpnews.pro/news/researchers-trick-fortune-500-ai-agents-into-running-arbitrary-code-via-llms-txt.md", "text": "https://wpnews.pro/news/researchers-trick-fortune-500-ai-agents-into-running-arbitrary-code-via-llms-txt.txt", "jsonld": "https://wpnews.pro/news/researchers-trick-fortune-500-ai-agents-into-running-arbitrary-code-via-llms-txt.jsonld"}}