How to suggest options that fit the user and don't repeat earlier ones (meals, restaurants, trips, activities, gifts, books). Use before any open-ended recommendation.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 runs `search_web_grounded` and `search_maps_grounded` to verify live facts, which pulls arbitrary outsider-authored web and map/review content that the agent must actively search for, so this is low risk rather than medium.
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.