Characterizing Security Effects of OSS Vulnerabilities in Agent Systems
cs.SE, cs.CR
Submitted: 2026-10-04
Updated: 2026-10-04
Code: https://github.com/aaif-goose/goose
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability
- Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem
- Towards Security-Auditable LLM Agents: A Unified Graph Representation
- Demystifying RCE Vulnerabilities in LLM-Integrated Apps
- MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
- Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications
- AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs
- MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning
- ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents
- Agentproof: Static Verification of Agent Workflow Graphs
- ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties