Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents

cs.CR, cs.AI

Submitted: 2026-10-02

Updated: 2026-10-02

Comments: 29 pages, 3 figures, including supplementary appendices. Preprint

Code: https://github.com/langchain-ai/langchain

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

Sources

• Defeating Prompt Injections by Design
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
• Towards Security-Auditable LLM Agents: A Unified Graph Representation
• Progent: Securing AI Agents with Privilege Control
• AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs

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