Preprint
Sep 2026
SkillSecurer: Detecting and Patching Prompt-Injection Vulnerabilities in AI Agent Skills
The results show that context-aware LLM analysis can provide reliable injection localisation and actionable remediation beyond skill-level flagging alone, and show that context-aware LLM analysis can provide reliable injection localisation and actionable remediation beyond skill-level flagging alone.
Donato Mecca, Alberto Verna, Youness Bouchari et al.
· 0 citations