Papers
arxiv:2607.21835

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

Published on Jul 23
Authors:
,

Abstract

ToolGuardian secures LLM agent-tool interactions via structured evidence collection and an Answer Set Programming policy layer for deterministic vetting and runtime authorization.

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy judgment into a single decision, or use heuristic/LLM enforcement that lacks deterministic, auditable reasoning over task context and multi-tool composition. This paper presents ToolGuardian, a policy-driven framework for securing agent-tool interactions through pre-admission vetting and task-aware runtime authorization. ToolGuardian uses progressive characterization to convert evidence into structured facts: descriptions capture declared intent, system-call traces expose coarse behavior, mock execution reveals observed effects, and source analysis identifies latent behavior. ToolGuardian's core contribution is an Answer Set Programming (ASP)-based declarative policy layer that reasons explicitly over capabilities, effects, task context, and composition. We compare ASP against heuristic and LLM-based policy realizations using identical inputs and output contracts. We evaluate ToolGuardian on 16 MCP-style tools, including 8 malicious variants derived from real open-source tools, and 20 runtime scenarios. For vetting, ASP reaches a deny-class F1 of 0.86 and 88% accuracy using description, syscall, and observed-effect evidence. For runtime authorization, fully specified realizations classify all scenarios correctly, while ablations show that removing compositional and conformance rules substantially degrades performance.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2607.21835
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2607.21835 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2607.21835 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2607.21835 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.