openbb-app-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's Reference mode (SKILL.md Phase 1) and the APP-INTERVIEW.md "Reference Example Analysis" explicitly instruct the agent to ingest and analyze third‑party code/URLs (e.g., GitHub, Streamlit Cloud, HuggingFace Spaces) and source URLs / web‑scraping targets, meaning untrusted external content is fetched and interpreted as part of the workflow.