motion-template-to-video
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by design, creating an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read and unpack user-supplied folders, ZIP files, and project assets including
index.htmlandTEMPLATE.md(as seen in the 'Open the supplied project' section). - Boundary markers: There are no explicit instructions to use boundary markers or to ignore embedded instructions within the ingested project files.
- Capability inventory: The skill possesses the capability to execute shell commands (via
node), perform file writes (motion_edit_project), and trigger network-based export jobs (motion_export_request). - Sanitization: No specific sanitization or validation steps for the content of the HTML/JS/Markdown files are mentioned before they are processed by the rendering engine.
- [COMMAND_EXECUTION]: The skill explicitly directs the agent to use host shell capabilities for rendering operations.
- Evidence: Instructions in the 'Unchanged: open it in the editor; changed: edit the working project' section provide a specific shell command template:
node /absolute/path/to/hyperframes/bin/hyperframes.mjs render /absolute/path/to/project-copy -o /absolute/path/to/output.mp4. - Context: This command execution is a core functional requirement for the skill's primary purpose of video production and uses a specific local runtime path.
Audit Metadata