nytid-todo

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly includes a "GitHub integration" section instructing the agent to "import" and "sync" GitHub issues/PRs (public, user-generated content) into the todo system, which the agent will read and use to create/manage tasks, so untrusted third-party content can influence actions.