Gelei Deng
2 papers · Latest:
Cryptography & Security
Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
A new supply-chain attack, DDIPE, poisons LLM coding agent skills by hiding malicious logic in documentation examples, bypassing strong defenses.
2604.03081
Cryptography & SecurityCredential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
Study reveals widespread credential leakage in LLM agent skills, identifying 520 vulnerable skills and 10 leakage patterns, primarily via debug logs.
2604.03070
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.