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 workflow calls get_events with detailed: true over the coming week (Phase 1, Step 2), which returns event titles and descriptions from calendar invitations that external senders can push onto the user's calendar without the agent selecting any item, and the workflow also tells the agent to capture tasks from the email inbox.
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.