pp-openart

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

• Third-party content exposure detected (medium risk: 0.30). The openart-pp-cli “direct use”/“agent mode” workflow accepts arbitrary user-provided flags like --prompt (and other free-text inputs such as which "<capability in your own words>") which the CLI then uses to call upstream OpenArt generation endpoints, so outsider-authored text is ingested at runtime as part of the request payload.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires running "npx -y @mvanhorn/printing-press install openart --cli-only" (SKILL.md:14-16), which fetches and executes remote npm package code at install time, so it is a runtime external dependency that executes remote code.