Trigger native web search. Use when you need quick internet research with concise summaries and full source URLs.
71
89%
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.
Runs a “native web search” tool during the required workflow, so the model ingests search-results/snippets that originate from public web content fetched at runtime and may contain attacker-controlled free text.
0865c84
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.