omc-doctor

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

• Third-party content exposure detected (high risk: 0.90). The Auto-Fix step "Missing/Outdated CLAUDE.md" explicitly uses WebFetch to retrieve raw markdown from the public GitHub URL (https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/main/docs/CLAUDE.md) and write it into ~/.claude/CLAUDE.md, which means the agent ingests untrusted, public third‑party content that can change configuration/behavior and thus could enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The Auto-Fix step issues a WebFetch to https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/main/docs/CLAUDE.md at runtime to retrieve raw markdown that is written into ~/.claude/CLAUDE.md, which can directly control agent prompts/configuration and therefore is a runtime external dependency that controls instructions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill instructs the agent to perform destructive and state-changing operations in the user's home directory (remove files/directories, modify settings.json, write CLAUDE.md, clear plugin caches) which can alter or delete user data—though it does not request sudo, change system-level files, or create users, so it's a moderate-risk state modification.