omarchy

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and extract manual pages from the public site https://learn.omacom.io (using full URLs like /2/the-omarchy-manual/...) and also provides commands that install themes from arbitrary git URLs (omarchy-theme-install ), so the agent will read and interpret untrusted external web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires fetching manual pages at runtime from https://learn.omacom.io (e.g. https://learn.omacom.io/2/the-omarchy-manual/...) and instructs the agent to extract and use that page content to form answers, so remote content directly controls the agent's prompts and is a required runtime dependency.