todoist-cli

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly includes commands that fetch and display open/public third‑party content—e.g., td hc view (public Help Center articles) and td attachment view / td comment view (user-uploaded files and comment text)—which the agent is expected to read as part of workflows and therefore exposes it to untrusted, user-generated content that could contain indirect instructions.