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

Luca Beurer-Kellner

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×3AI×3

Frequent co-authors

Aleksei Kudrinskii2×
Marco Milanta2×
Kristian Bonde Nielsen2×
Hemang Sarkar2×
Liran Tal2×
Debeshee Das1×

Research Timeline

2026
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

The paper introduces Trojan Hippo, a persistent memory attack that exfiltrates sensitive data from LLM agents by planting dormant payloads into long-term memory, and develops a comprehensive framework to evaluate defenses against it.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

The paper analyzes a large sample of AI agent skills, revealing that a significant percentage contain critical security vulnerabilities and malicious payloads, necessitating automated security analysis.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

The paper analyzes a large corpus of AI agent skills, identifying a significant percentage of malicious payloads that pose serious security risks to users and systems.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 27, 2026

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

Luca Beurer-Kellner, Aleksei Kudrinskii, Marco Milanta, Kristian Bonde Nielsen +2 more

The paper analyzes a large sample of AI agent skills, revealing that a significant percentage contain critical security vulnerabilities and malicious payloads, necessitating automated security analysi…

View →
cs.CRcs.AIRecentMay 27, 2026

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

Luca Beurer-Kellner, Aleksei Kudrinskii, Marco Milanta, Kristian Bonde Nielsen +2 more

The paper analyzes a large corpus of AI agent skills, identifying a significant percentage of malicious payloads that pose serious security risks to users and systems.

View →
cs.CRcs.AIRecentMay 3, 2026

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

Debeshee Das, Julien Piet, Darya Kaviani, Luca Beurer-Kellner +2 more

The paper introduces Trojan Hippo, a persistent memory attack that exfiltrates sensitive data from LLM agents by planting dormant payloads into long-term memory, and develops a comprehensive framework…

View →