@tank/frontend-craft

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for this skill is the offline-first CLI search/install, which reads cached registry catalog JSON (including outsider-authored description, name, type, addCommandArgument) from scripts/.cache/all-registries-components.json and then formats it into LLM-readable stdout text via scripts/search-components.py → format_results() / print(json.dumps(results)).