设计稿还原规则。先输出布局分析报告,再按需加载模版
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches runtime templates from skill://bkui-builder/... (e.g., skill://bkui-builder/assets/layouts/admin-layout-dark.vue and skill://bkui-builder/references/visual-mapping.md) via "FetchMcpResource", and those fetched templates are loaded at runtime to drive the agent's code-generation/behavior, so external content can directly control the agent's output.
9f98ece
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.