Chia-Mu Yu

This paper introduces Dependency Steering, a novel attack paradigm demonstrating that malicious agent skills can actively bias LLM coding agents to use attacker-controlled packages, posing a significant, hard-to-detect software supply chain risk.

The paper introduces Neutral Prompting Attacks (NPA), a stealthy method showing that semantically benign prompts can covertly increase package hallucination in coding agents, creating new software supply chain risks.

The paper introduces Reasoning Exposure Prompting (REP), a method that demonstrates that even when LLMs hide internal reasoning traces from users, useful reasoning supervision can still be elicited through specialized prompting.

The paper introduces Reasoning Exposure Prompting (REP), a method that demonstrates that even when LLMs hide their internal reasoning steps from users, useful reasoning supervision can still be elicited through specialized prompting.

The paper identifies Mid-Session Tool Injection (MSTI) as a novel threat in the WebMCP protocol, demonstrating that attackers can manipulate the visible or perceived set of tools available to AI agents during an active session.