openclip-repurpose
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill connects to official infrastructure at openclip.app for its remote MCP server transport and authentication token generation. These connections match the identity of the author, OpenClip-App.
- [PROMPT_INJECTION]: The skill ingests untrusted data via video URLs and file uploads through the submit_video tool, creating a surface for indirect prompt injection. While the agent possesses capabilities such as render_clip and edit_video, the skill's instructions do not include specific sanitization or boundary markers for the external content.
Audit Metadata