Skip to content

Hide Navigation Hide TOC

Hidden LLM Instructions in Skill Descriptions - ATR-2026-00155 (c3908a67-59da-5237-a1a2-805e6566a24d)

Detects skills that embed hidden instructions directed at the LLM using phrases like "CRITICAL INSTRUCTION — YOU MUST FOLLOW THIS" or "Before doing ANYTHING". These instructions can manipulate the LLM to bypass normal security checks, skip validation steps, or follow alternative workflows that may compromise security. The analyzed BlogBurst skill contains "CRITICAL INSTRUCTION — YOU MUST FOLLOW THIS" followed by specific behavioral directives.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Hidden LLM Instructions in Skill Descriptions - ATR-2026-00155 (c3908a67-59da-5237-a1a2-805e6566a24d) Agent Threat Rules 1