takt-facet-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows explicitly instruct the agent to fetch and read external, user-generated sources — e.g., gather-review.md directs running "gh pr view / gh pr diff" to pull PR descriptions/diffs and research-dig.md/plan.md instruct downloading and reading public datasets or external "参照資料" — so the agent will ingest untrusted third-party content that can influence its actions.