Sep 2026· International Journal of Innovative Science and Research Technology· pp. 2451· 0 citations· 19 references
TL;DR
The results indicate that moving enforcement from the session boundary to the action boundary can reduce implicit trust, constrain privilege propagation, and improve auditability while preserving useful autonomy.
Abstract
Agentic artificial intelligence expands the enterprise security boundary because autonomous agents can plan
tasks, retain memory, invoke tools, call APIs, and initiate business actions. Authentication at session start is therefore
insufficient when later actions may be influenced by untrusted content, poisoned memory, compromised tools, or excessive
delegated privilege. This paper proposes the Zero Trust Agentic AI Security Framework (ZT-AASF), a vendor-neutral
architecture that applies continuous verification to consequential agent actions. The framework separates six control
planes: identity and delegation, context and data trust, policy and risk decision, tool and action enforcement, runtime
observability, and containment and recovery. A contextual authorization model evaluates delegated scope, source
provenance, data sensitivity, tool risk, behavioral deviation, and action impact before execution. A design-level evaluation
against ten OWASP agentic risk classes produces 27 of 30 control-coverage points for ZT-AASF versus 5 of 30 for a
conventional integration baseline. These values represent architectural coverage, not measured attack-prevention rates.
The results indicate that moving enforcement from the session boundary to the action boundary can reduce implicit trust,
constrain privilege propagation, and improve auditability while preserving useful autonomy.
Enterprise adoption of generative AI is shifting from passive question answering to autonomous agentic execution. Modern agents can decompose goals, retrieve business context, call tools, update records, send messages, initiate transactions, and coordinate workflows across multiple systems. This creates productivity op...
S. Ray· International Journal of Glo...· 0 citations
Language-model agents commonly collapse two decisions that security systems separate: selecting an action and determining whether that action is authorized. When a model exercises standing authority, indirect prompt injection can convert influence over its reasoning into unauthorized effects. We present AgentCap, a run...
Security operations centers (SOCs) are increasingly utilizing AI agents for various functions, including alert triaging and support of ITDR workflows. These agents, identified as non-human enterprise identities with API tokens and delegated authority, pose a risk due to insufficient validation of their actions against...
Tuhin Banerjee, Sharad Sharma, B. Singh et al.· 2026 International Conferenc...· 0 citations
The rapid adoption of autonomous artificial intelligence (AI) agents in cloud environments has introduced new security challenges due to their ability to dynamically select tools, access heterogeneous resources, interpret external information, and modify execution plans at runtime. Conventional authentication and stati...
Reshma Mavkar, Sarita B. Patil, Nitin S. Shrirao et al.· Journal of Future Internet a...· 0 citations