pack-source-process

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

• Third-party content exposure detected (high risk: 1.00). Yes — SKILL.md explicitly instructs the agent to gather and process community sources such as migration guides, blog posts, GitHub issues and framework changelogs (see "Step 1: Source Prioritization" and the "## Source: [title/url]" extraction template in Step 2), which are untrusted public/user-generated web content the agent must read and use to derive corrective actions.