{"ID":2894960,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.10457","arxiv_id":"2507.10457","title":"Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems","abstract":"The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces Logic-layer Prompt Control Injection (LPCI), a novel category of attacks that embeds encoded, delayed, and conditionally triggered payloads within memory, vector stores, or tool outputs. These payloads can bypass conventional input filters and trigger unauthorised behaviour across sessions.","short_abstract":"The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces Logic-layer Prompt Control Injection (LPCI), a novel category of attacks that embeds enc...","url_abs":"https://arxiv.org/abs/2507.10457","url_pdf":"https://arxiv.org/pdf/2507.10457v2","authors":"[\"Hammad Atta\",\"Ken Huang\",\"Manish Bhatt\",\"Kamal Ahmed\",\"Muhammad Aziz Ul Haq\",\"Yasir Mehmood\"]","published":"2025-07-14T16:37:05Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}