The ‘Skill’ Gap: How Minor Text Tweaks Can Turn AI Agents Into Security Risks
Researchers from the University of Maryland reveal how simple natural language edits in SKILL.md files can bypass security scanners and hijack AI agents.
Tag: artificial intelligence agents
The ‘Skill’ Gap: Researchers Warn AI Agents Can Be Hijacked via Natural Language Instructions
Researchers from the University of Maryland reveal how minor semantic edits to AI agent 'skills' can bypass security scanners and lead to prompt injection attacks.
The ‘Semantic’ Supply Chain: How Minor Text Edits Can Turn AI Agents Rogue
Researchers from the University of Maryland reveal how small changes to natural language in AI skill files can bypass security filters and hijack agent behavior.