SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime

ArXi:2602.19555v2 Announce Type: replace-cross Agentic systems based on large language models (LLMs) operate not merely as text generators but as autonomous entities that dynamically retrieve information and invoke tools. This execution model shifts the attack surface from traditional build-time artifacts to inference-time dependencies, exposing agents to manipulation through untrusted data and probabilistic capability resolution. While prior work has examined model-level vulnerabilities, security risks arising from the complex, cyclic runtime behavior of agents remain fragmented.