4todo

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly requires calling the third‑party 4to.do API (https://4to.do/api/v0 — e.g., GET /workspaces and GET /todos) and reading user-created workspace and todo names as part of normal operation, so arbitrary user-generated content from that API could influence the agent's decisions and actions.