Reachability Is Only the Beginning: Toward Effect-Aware Vulnerability Analysis for AI Agents
Open Access
- 8 October 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 17-20
Abstract
AI agents increasingly rely on tools built on or dependent on open source software (OSS) to access data, invoke services, and modify external resources. Vulnerabilities in these dependencies can there- fore propagate into agent systems. Conventional analyses trace vulnerability effects through explicit program states and data or control dependencies. Agent systems introduce model inference be- tween tool output and subsequent action, so affected states become model-visible observations whose influence depends on semantic interpretation. Program analysis can show that such values reach model input, but not whether they change the generated action or external system. We assess three successive links in this process. Vulnerable execution must change the observation, the changed observation must influence the generated action, and the executed action must change an external resource. Our framework combines program tracing, repeated executions under matched contexts, and external state verification to establish these links.Keywords
Funding Information
- Major Technological Innovation Program of HUST (2025ZDKJCX05)
This publication has 13 references indexed in Scilit:
- Securing AI Agents with Information-Flow ControlarXiv, 2025
- Evaluation and Benchmarking of LLM Agents: A Survey2025
- System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control PerspectivearXiv, 2024
- Causal Reasoning and Large Language Models: Opening a New Frontier for CausalityarXiv, 2024
- InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents2024
- Software Composition Analysis for Vulnerability Detection: An Empirical Study on Java Projects2023
- On the Security Blind Spots of Software Composition Analysis2023
- SoK: Taxonomy of Attacks on Open-Source Software Supply Chains2023
- Understanding the Threats of Upstream Vulnerabilities to Downstream Projects in the Maven Ecosystem2023
- Demystifying the vulnerability propagation and its evolution via dependency trees in the NPM ecosystem2022