前端权限控制方案 (IAM)
基于蓝鲸 IAM 的前端鉴权方案，包含 v-authority 指令实现、权限组件封装及无权限交互规范。
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
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.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill references a runtime asset "skill://permission-directive/assets/authority-directive.ts", which indicates fetching executable TypeScript (the directive implementation) at runtime and thus could execute remote code and control agent behavior.
- Repository
- TencentBlueKing/bk-bcs
- Commit
99ba07d
- 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.