smart-search
通过xiaobei受管浏览器搜索和阅读网页：选择站点、构造搜索 URL、使用默认或平台专用的持久化 session 并提取真实结果。如果已有 douyin-hunter、xhs-hunter、tiktok-hunter、kuaishou-hunter、x-hunter、weibo-hunter 或 wx-mp-hunter 技能，对应平台的内容搜索应该优先调用上面这些技能。
77%
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/smart-search/SKILL.mdW011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The workflow reads GitHub issues and pull requests via browser search and reading rules, which are authored by outsiders and expose the agent to indirect prompt injection.
- Repository
TeamWiseFlow/xiaobei
- Revision
47aea0b
- Audited
- Security analysis
Is this your skill?
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.