{"slug": "decision-models-vulnerable-to-indirect-prompt-injection-attacks", "title": "Decision Models Vulnerable to Indirect Prompt Injection Attacks", "summary": "Researchers at HiddenLayer found that decision models such as System One are vulnerable to indirect prompt injection attacks, facing risks similar to those of autoregressive models. In a simulated test, a browser agent was tricked into clicking a malicious link via crafted prompts.", "body_md": "Researchers at HiddenLayer discovered that decision models, like System One, are surprisingly vulnerable to indirect prompt injection attacks, facing similar risks as autoregressive models. A simulated test even showed a browser agent could be tricked into clicking a malicious link through cleverly crafted prompts.", "url": "https://wpnews.pro/news/decision-models-vulnerable-to-indirect-prompt-injection-attacks", "canonical_source": "https://osintsights.com/decision-models-vulnerable-to-indirect-prompt-injection-attacks", "published_at": "2026-10-15 07:09:58+00:00", "updated_at": "2026-10-15 07:13:09.879118+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "ai-agents"], "entities": ["HiddenLayer", "System One"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/decision-models-vulnerable-to-indirect-prompt-injection-attacks", "markdown": "https://wpnews.pro/news/decision-models-vulnerable-to-indirect-prompt-injection-attacks.md", "text": "https://wpnews.pro/news/decision-models-vulnerable-to-indirect-prompt-injection-attacks.txt", "jsonld": "https://wpnews.pro/news/decision-models-vulnerable-to-indirect-prompt-injection-attacks.jsonld"}}