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 morning schedule review and evening tomorrow-preview steps read the user's calendar, where external senders can place event invites and descriptions without the agent selecting a specific item, so this is plausibly outsider-authored text in a monitored feed.
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.