Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
67%
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
Fix and improve this skill with Tessl
tessl review fix ./skills/research-codex-en/research/SKILL.mdThe 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 research skill workflow ingests user-provided text via the `/research <topic>` trigger to construct a web-search-agent prompt (Step 2 “Web Search Supplement”), meaning an outsider’s free text can influence the agent that performs web browsing/search and then reads extracted source content at runtime.
Weizhena/Deep-Research-skills
6ce38f6
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.