generate-theories

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses the Theorizer (accessed via asta-gateway) to "search papers, extract evidence, form theories" and the SKILL.md submission/polling workflow (Steps 1 and 4) shows it retrieves and ingests external research papers as part of its required pipeline, meaning untrusted third‑party content is read and directly drives theory generation and downstream actions.