sync-back-merge

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs reading GitHub Issues (via gh issue view on xu-cell/ai-engineering-init) to extract user-submitted diffs and then apply those edits to source SKILL.md files, so it ingests untrusted, user-generated third‑party content that can change agent actions.