rmmz-scene

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored free text via the external Registry when the user runs rmmz-scene search ... --json and rmmz-scene info ... --json, which are then parsed for decisions without requiring a specific preselected item beyond user-supplied search parameters.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime installation command that fetches and installs remote code (git+https://github.com/lemonhall/rmmz-scene-registry.git), which will execute/introduce external code the CLI relies on.