omc-setup

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 explicitly mandates running a setup script that downloads the canonical CLAUDE.md (with a fallback to https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/main/docs/CLAUDE.md) and other steps (Phase 2 uses npm view and Phase 4 may call the GitHub API), so the agent fetches and ingests public GitHub/npm content which is untrusted third‑party data and can materially alter agent behavior via injected rules/context.