SkillsMP

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

15:08

2026-09-22

letsdatascience.com

ai-agents

Wake Forest researcher tells LDS what AI skill security checks can miss

A study of credential leakage in third-party AI agent skills found 520 affected skills containing 1,708 issues, of which 437 were classified as vulnerable and 83 as malicious, according to Wake Forest…

18:21

2026-08-26

arxiv.org

artificial-intelligence

Credentials Are Leaked by LLM Agent Skills: An Empirical Study

A new empirical study from researchers on arXiv analyzed 17,022 skills sampled from 170,226 artifacts on SkillsMP, the largest open-source skill marketplace, and found 520 affected skills containing 1…

// co-occurs with top 5 entities

Ying Zhang 1 Wake Forest University 1 Lets Data Science 1 arXiv 1 Yi Liu 1

// topics top 4 topics

ai agents 2 ai safety 2 ai research 2 artificial intelligence 2