The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the shell permission to execute the mediakit-cli utility, which is used to process media files based on user-provided parameters.
[EXTERNAL_DOWNLOADS]: The documentation instructs the user to install the @volcengine/mediakit-cli package from the official NPM registry. This package is an official resource from the skill's authoring organization.
[PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection through the processing of untrusted external media data. Ingestion points: Untrusted data enters the agent context through parameters such as video_url, audio_url, subtitle_url, and the subtitles text array defined in SKILL.md and related reference files. Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat this data as purely non-executable or to ignore any instructions embedded within the media metadata or subtitle text. Capability inventory: The skill uses the shell to run mediakit-cli for media processing tasks. Sanitization: There is no mention of input sanitization or validation performed on the content of these external files before processing.

byted-mediakit-editing