fixing

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows explicitly instruct external web research and ingestion of public content — e.g., references/workflow-deep.md Step 2 directs the "researcher" subagent to "Search latest docs, best practices" and references/workflow-ui.md includes search scripts (python3 .../search.py) and use of chrome/devtools, which require fetching and interpreting open/public third‑party pages that can influence subsequent actions.