Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections

Abstract

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based on instructions stored in simple markdown files. Although Agent Skills can be a very useful tool, we show that they are fundamentally insecure, since they enable trivially simple prompt injections. We demonstrate how to hide malicious instructions in long Agent Skill files and referenced scripts to exfiltrate sensitive data, such as internal files or passwords. Importantly, we show how to bypass system-level guardrails of a popular coding agent: a benign, task-specific approval with the "Don't ask again" option can carry over to closely related but harmful actions. Overall, we conclude that despite ongoing research efforts and scaling model capabilities, frontier LLMs remain vulnerable to very simple prompt injections in realistic scenarios. Our code is available at https://github.com/aisa-group/promptinject-agent-skills.

Repository Summary

This paper shows that skill files themselves can become a powerful prompt-injection surface, enabling realistic attacks with very low implementation complexity and highlighting a new security problem unique to skill-augmented agent ecosystems.

Bibliographic Data

Title

Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections

Authors

David Schmotz, Sahar Abdelnabi, Maksym Andriushchenko

Publication date

2025/10/30

Identifier

arXiv:2510.26328

DOI

10.48550/arXiv.2510.26328

PDF size

2.2 MB