Trust propagation and structural containment in Multi-agent LLM pipelines

arXiv:2609.17648 · cs.CR, cs.CY · Submitted 2026-09-15 · Read on arXiv

cs.CR, cs.CY

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: Accepted at IEEE Cyber Awareness & Research Symposium (CARS), 2026

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

Terminology

• Ablation — 13× in this paper · explained in 1 episode
• Agent Hijacking — 9× in this paper · explained in 1 episode
• Agentic AI — 8× in this paper · explained in 1 episode
• Verification — 5× in this paper · explained in 2 episodes
• Judgment Bypass Rate — 4× in this paper
• Multi-Agent System — 4× in this paper · explained in 6 episodes
• AI Agents — 3× in this paper · explained in 2 episodes
• Provenance — 3× in this paper · explained in 4 episodes
• Unsafe Action Rate — 3× in this paper
• Agentic AI systems — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Model Context Protocol — 2× in this paper
• Agentic AI Framework — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes

Sources

• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
• Ignore Previous Prompt: Attack Techniques For Language Models
• LLM Agents Should Employ Security Principles
• Firewalls to Secure Dynamic LLM Agentic Networks
• Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
• Jatmo: Prompt Injection Defense by Task-Specific Finetuning
• Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications
• ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications
• Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents
• SoK: The Attack Surface of Agentic AI - Tools and Autonomy
• Are AI-assisted Development Tools Immune to Prompt Injection?
• Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
• Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System

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