pp-midjourney

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

• Third-party content exposure detected (medium risk: 0.30). Source: the midjourney-pp-cli “explore”/“queue”/“generations”/etc commands can fetch Midjourney discovery feeds and account job/queue data over HTTP at runtime, meaning outsider-authored free text from third-party/inside-Midjourney content can be ingested when the authenticated agent runs those commands.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's install instructions explicitly run remote installers that fetch and execute code at runtime (e.g., "go install github.com/mvanhorn/printing-press-library/library/ai/midjourney/cmd/midjourney-pp-cli@latest" and "go install github.com/mvanhorn/printing-press-library/library/ai/midjourney/cmd/midjourney-pp-mcp@latest"), so these GitHub module URLs are runtime-executed dependencies.