When Skills Lie: Hidden-Comment Injection in LLM Agents

LLM agents often rely on Skills to describe available tools and recommended procedures. We study a hidden-comment prompt injection risk in this documentation layer: when a Markdown Skill is rendered to HTML, HTML comment blocks can become invisible to human reviewers, yet the raw text may still b...

PT-2022-17534 · Amazon · Amazon Echo Dot

Name of the Vulnerable Software and Affected Versions: Amazon Echo Dot devices, 3rd and 4th Generation Description: The issue allows for arbitrary voice command execution on affected devices. This can be achieved by a remote attacker using a malicious skill or by a physically proximate attacker...