omc-setup

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

• Third-party content exposure detected (high risk: 0.90). The setup explicitly downloads and installs a public CLAUDE.md from GitHub (phases/01-install-claude-md.md mandates running the setup script and fallbacks to https://raw.githubusercontent.com/.../docs/CLAUDE.md) and then uses that file's content (which includes context-persistence tags and configuration) as part of the required workflow, so arbitrary third-party content could influence agent behavior and tool use.

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

• Potentially malicious external URL detected (high risk: 0.90). The setup mandates running a script that may fetch the canonical CLAUDE.md at runtime (fallback: https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/main/docs/CLAUDE.md), and that CLAUDE.md contains context/instruction tags that directly control agent prompts/instructions and is required by the setup, so this is a high-risk runtime external dependency.