pith. sign in

Yuekang Li

Identifiers

  • name variant Yuekang Li 0.60 · backfill

Papers (14)

  1. SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents cs.CR · 2026 · author #5
  2. MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content cs.CR · 2026 · author #5
  3. Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks cs.SE · 2026 · author #5
  4. Membership Inference Attacks Against Video Large Language Models cs.CR · 2026 · author #6
  5. LOLGORITHM: Funny Comment Generation Agent For Short Videos cs.CV · 2026 · author #6
  6. Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems cs.CR · 2026 · author #5
  7. Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study cs.CR · 2026 · author #5
  8. Where Code Meets Natural Language: Taxonomy-Driven Information Flow Analysis for LLM-Integrated Applications cs.SE · 2026 · author #4
  9. "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills cs.CR · 2026 · author #5
  10. Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale cs.CR · 2026 · author #7
  11. Prompt to Pwn: Automated Exploit Generation for Smart Contracts cs.CR · 2025 · author #3
  12. Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment cs.CR · 2024 · author #3
  13. Prompt Injection attack against LLM-integrated Applications cs.CR · 2023 · author #3
  14. Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study cs.SE · 2023 · author #4

Mentions

  • 2602.06547 #5 · arxiv_oai · confidence 0.70 Yuekang Li
  • 2605.28122 #5 · arxiv_oai · confidence 0.70 Yuekang Li
  • 2605.28116 #5 · arxiv_oai · confidence 0.70 Yuekang Li
  • 2603.28345 #4 · arxiv_oai · confidence 0.70 Yuekang Li
  • 2605.18583 #5 · arxiv_oai · confidence 0.70 Yuekang Li
  • 2305.13860 #4 · arxiv_oai · confidence 0.70 Yuekang Li

Frequent Coauthors