Research a topic or check a fact, with a source for each claim. Use when the user asks you to research a topic, verify a fact, or collect facts from official docs, specs, or APIs.
85%
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 has the agent run web searches and open arbitrary web pages (SKILL.md lines 10-11), which are outsider-authored and selected by search rather than forced delivery, so this is low risk.
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.