The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the user to install the @volcengine/mediakit-cli package from the npm registry. This is a legitimate vendor resource provided by Volcano Engine, the author of the skill, and is necessary for the skill's primary functionality.
[COMMAND_EXECUTION]: The skill operates by executing shell commands using the mediakit-cli binary to perform audio and video analysis. This behavior is consistent with the skill's stated purpose of providing media kit capabilities.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes data from external URLs.
Ingestion points: The audio_url and video_url parameters in the separate-voice and probe-audio-metadata tools allow the agent to fetch and process remote media files.
Boundary markers: The skill documentation does not specify the use of boundary markers or clear instructions for the agent to ignore any potential instructions embedded within media metadata or headers.
Capability inventory: The skill has the capability to execute shell commands via the mediakit-cli tool.
Sanitization: There is no mention of explicit sanitization or validation of the content retrieved from external URLs before it is processed by the CLI tool or interpreted by the agent.

byted-mediakit-audio