The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required sync workflow fetches remote Todoist task content (titles, notes, and due/status fields) at line 170, and that free text could in principle come from collaborators on shared Todoist projects, which is a weak, indirect path to outsider authorship rather than a clear public submission queue.
kmondlane/ExoMind
8794d26
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.