LLM07
Insecure Plugin Design
Vulnerabilities in LLM plugins, function calling, tool use
137 papers Browse all papers
Monthly publications
Paper types
defense 42
attack 35
benchmark 33
survey 22
tool 5
Domains
nlp 137
multimodal 12
reinforcement-learning 2
graph 1
vision 1
audio 1
Co-occurring categories
Other OWASP categories that appear on the same papers
LLM01 Prompt Injection
89 LLM08 Excessive Agency
55 ML06 AI Supply Chain Attacks
17 LLM06 Sensitive Information Disclosure
8 LS07 Blue-Team Agents
5 LS06 Red-Team Agents
5 LLM04 Model Denial of Service
4 LS10 Benchmarks & Evaluation
3 LS01 Vulnerability Discovery
3 ML09 Output Integrity Attack
2 ML10 Model Poisoning
2 ML01 Input Manipulation Attack
2 ML02 Data Poisoning Attack
1 LS04 Patch & Remediation
1 LS03 Reconnaissance & OSINT
1 LS02 Exploit Generation
1Top cited papers
1102938485868788897106
Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
2025 survey
MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers
2025 survey
Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
2025 survey
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
2026 tool
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
2025 survey
When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation
2025 benchmark
A Survey on Agentic Security: Applications, Threats and Defenses
2025 survey
Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections
2025 attack
Securing AI Agent Execution
2025 defense
Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
2025 attack