3 papers
cs.CR2026
No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers
Zehua Zhang, Jie Hu, Pratham Hegde +14
Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely…
cs.CR2026
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills
Wenhui He, Yue Li, Bang Fu +4
Programmatic skills in LLM ecosystems consist of a natural-language description and executable implementation files. Users and LLMs rely on the description to understand the skill'…
cs.SE2025
BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Zehua Zhang, Ati Priya Bajaj, Divij Handa +14
Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on…