The Agent Skills Directory

[SAFE]: The skill's primary function is code translation and validation. The included Python and Bash scripts are designed to support this workflow through linting, rendering, and visual comparison.
[COMMAND_EXECUTION]: The skill utilizes subprocess calls to external tools including ffmpeg, ffprobe, npm, and node. These operations are limited to the intended purpose of rendering video compositions and managing project dependencies within the provided test corpus. The scripts use standard security practices, such as quoting shell variables, to mitigate common command injection risks.
[EXTERNAL_DOWNLOADS]: The test orchestrator (assets/test-corpus/run.sh) invokes npm install to fetch necessary dependencies for the Remotion fixtures. These downloads are performed from the official npm registry, which is a well-known and trusted service.
[DATA_EXFILTRATION]: No patterns indicative of sensitive data exfiltration or unauthorized network communication were detected. Network calls found in specific .tsx test cases (e.g., tier-4-escape-hatch/cases/03-async-metadata.tsx) are intended as illustrative examples of unsupported patterns for the linter and are not executed by the skill's infrastructure.
[PROMPT_INJECTION]: The instructions focus on the mechanical translation of code and do not contain directives aimed at bypassing safety filters or overriding core agent behavior.

remotion-to-hyperframes