marketing-loops

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

• Third-party content exposure detected (medium risk: 0.30). The runtime CLI in resources/loop-model.js ingests attacker-supplied JSON from process.argv (parsed via JSON.parse(raw) for score/project) and uses its free-text fields like stages[].name directly in rendered output, so the workflow can ingest outsider-authored free text.