이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.
에이전트 요청
Review the Skillstore skill "hyperframes-cli" from https://skillstore.io/skills/heygen-com-hyperframes-cli.md and its manifest at https://skillstore.io/api/skills/heygen-com-hyperframes-cli/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.
에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.
에이전트가 읽기 쉬운 리소스
AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.
Static matches are predominantly Markdown examples and documentation references, not executable behavior in this skill. The skill nevertheless guides users through real external operations, including project uploads, cloud deployment, publication, feedback submission, and URL-based capture; these require explicit user consent and credential review.
Hosted cloud rendering uploads a project archive. Users can unintentionally upload source assets or secrets if they do not review the project before rendering.
The documentation explicitly describes project upload and exclusions, which establishes an external data-transfer boundary.
Cloud Run deployment provisions billable resources, and its destroy operation removes the scratch bucket. These side effects require explicit user approval.
The documented deploy and destroy operations have clear infrastructure, cost, and deletion effects.
The skill instructs agents to capture feedback after a run, while publishing or filing an issue can send project material outside the local environment. Require confirmation before either action.
These sections describe external feedback and publication workflows, creating a clear consent and disclosure boundary.
Unrestricted URL capture and callbacks are network trust boundaries
Capture accepts website URLs and cloud rendering accepts callback URLs. Do not use untrusted or internal addresses without validation and explicit approval.
The documented commands accept caller-supplied URLs and initiate network-facing workflows; address restrictions are not stated.