It is demonstrated that ActGov can enforce fine-grained authorization over dynamic agent executions without relying on the underlying LLM to correctly identify malicious instructions, significantly outperforming existing defenses.
Abstract
Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing defenses isolate injected content or constrain execution with predefined plans and static policies, but these approaches are brittle under dynamic workflows and scale poorly across extensible tool ecosystems. In this work, we present ActGov, a runtime enforcement framework that validates each LLM-proposed tool action before it causes external effects. Built on a unified semantic model of authorization, actions, runtime context, and security constraints, the ActGov-Policy component iteratively constructs a policy set from tool specifications, benign tasks, and observed failure traces, with each update verified through SMT-based counterexample checking. At runtime, ActGov-Runtime abstracts each tool call into finite policy records and permits it only if it remains within the task-scoped authorization boundary and satisfies all applicable policies. This per-action enforcement preserves authorization throughout long-horizon, dynamically branching workflows. We evaluate ActGov on the AgentDojo and AgentDyn benchmarks across multiple models and attack configurations. It shows that ActGov consistently reduces the success rate of indirect prompt-injection attacks while preserving task utility, significantly outperforming existing defenses. These results demonstrate that ActGov can enforce fine-grained authorization over dynamic agent executions without relying on the underlying LLM to correctly identify malicious instructions.
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...
Tool-using large language model (LLM) agents translate model outputs into consequential actions, turning indirect prompt injection into an execution-security problem. Existing defenses constrain tool calls, trajectories, or information flows, but often leave action semantics, state dependencies, and evidence relations...
Guo-Qin Xiong, Sheng-Tao Wen, Xiang Chen et al.· 0 citations
Agentic systems increasingly fulfill user requests through multi-step tool workflows over files, services, and external resources. In these workflows, isolated per-call checks can miss a workflow-level failure: each call may be locally admissible, but the sequence can exceed the authorization boundary established for t...
These results demonstrate DCCs as a reusable semantic foundation for agent autonomy across heterogeneous devices, unifying capability-based planning, evidence-grounded execution, and authorized recovery within one architecture.
Xue-Chun Li, Jia-Xin Liang, Jie Li et al.· arXiv.org· 0 citations
EffectMatch is presented, a runtime that collects persistent changes within a controlled execution boundary and compares them with what the application approved for the current state and execution and blocks the silent acceptance and downstream propagation of persistent outcomes inconsistent with application approval.
A state-bound runtime assurance layer that separates probabilistic measurement from deterministic adjudication, binds an execution allowance to the decision-relevant basis of an approval, invalidates that allowance after relevant logged changes, and rechecks admissibility at dispatch distinguishes the continued validit...
Jayesh Bhadane, Ramachandra Yerramsetti, Rajesh Gupta et al.· 0 citations