ndi-docs

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

• Third-party content exposure detected (high risk: 0.95). At runtime the skill fetches and text-extracts outsider-authored free text from fixed public URLs (e.g., docs.ndi.video HTML pages and the GitHub raw README for DistroAV) via urllib.request.urlopen() in fetch_url() → extract_text() → cached text that is then printed/used by search/section.