ToolGuardian: Declarative Security for AI Agent-Tool Interactions

arXiv:2607.21835 · cs.CR, cs.AI · Submitted 2026-07-23 · Read on arXiv

Arun Ravindran, Saurabh Deochake

cs.CR, cs.AI

Submitted: 2026-07-23

Code: https://github.com/cisco-ai-defense/mcp-scanner

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 21× in this paper · explained in 2 episodes
• Ablation — 16× in this paper · explained in 1 episode
• Accuracy — 12× in this paper · explained in 1 episode
• Trace — 11× in this paper · explained in 2 episodes
• Provenance — 9× in this paper · explained in 3 episodes
• Answer Set Programming — 8× in this paper
• Model Context Protocol — 4× in this paper
• AI Agents — 3× in this paper · explained in 2 episodes
• Agentic AI — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Answer Set Programming (ASP) — 3× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Agent Memory — 2× in this paper · explained in 1 episode
• Agent Skills — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Agentic AI Workflows — 1× in this paper · explained in 1 episode
• Agentic AI systems — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• National Institute of Standards and Technology — 1× in this paper

Sources

• MalTool: Malicious Tool Attacks on LLM Agents
• "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
• MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
• MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols
• Progent: Securing AI Agents with Privilege Control
• ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
• AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
• AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs