alphagbm-theme-research

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and displays "recent matched news" and an AI-generated "theme_summary" from the external AlphaGBM API (e.g., GET /api/research/themes/<THEME_ID> on https://alphagbm.zeabur.app), which clearly ingests public/untrusted news content that the agent reads and uses in its workflow.