Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yanjie Zhao

Yanjie Zhao

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3Software Eng.×2

Frequent co-authors

Haoyu Wang3×
Shenao Wang2×
Yue Liu1×
Yunbo Lyu1×
Ting Zhang1×
David Lo1×

Research Timeline

2026
"Elementary, My Dear Watson." Detecting Malicious Skills via Neuro-Symbolic Reasoning across Heterogeneous Artifacts

The paper introduces MalSkills, a neuro-symbolic framework that detects malicious skills in the expanding agentic supply chain by analyzing security-sensitive operations across heterogeneous artifacts.

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions

This paper introduces Agentic Workflow Injection (AWI), a new class of vulnerability in LLM-powered GitHub Actions, and presents TaintAWI, a novel taint-analysis tool that identifies hundreds of exploitable zero-day vulnerabilities.

How Agentic AI Coding Assistants Become the Attacker's Shell

The paper analyzes how agentic AI coding assistants can be compromised via prompt injection attacks embedded in external artifacts, turning them into unauthorized execution shells for attackers.

Highlighted terms show continued research focus across papers

Papers

cs.SEcs.CRRecentMay 25, 2026

How Agentic AI Coding Assistants Become the Attacker's Shell

Yue Liu, Yanjie Zhao, Yunbo Lyu, Ting Zhang +2 more

The paper analyzes how agentic AI coding assistants can be compromised via prompt injection attacks embedded in external artifacts, turning them into unauthorized execution shells for attackers.

View →
cs.CRRecentMay 8, 2026

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions

Shenao Wang, Xinyi Hou, Zhao Liu, Yanjie Zhao +4 more

This paper introduces Agentic Workflow Injection (AWI), a new class of vulnerability in LLM-powered GitHub Actions, and presents TaintAWI, a novel taint-analysis tool that identifies hundreds of explo…

View →
cs.CRcs.SERecentMar 28, 2026

"Elementary, My Dear Watson." Detecting Malicious Skills via Neuro-Symbolic Reasoning across Heterogeneous Artifacts

Shenao Wang, Junjie He, Yanjie Zhao, Yayi Wang +2 more

The paper introduces MalSkills, a neuro-symbolic framework that detects malicious skills in the expanding agentic supply chain by analyzing security-sensitive operations across heterogeneous artifacts…

View →