The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides templates for executing npx remotion render and npx remotion still commands. These are legitimate operations for the primary purpose of video rendering using the vendor's toolset.
[INDIRECT_PROMPT_INJECTION]: The skill instructions facilitate a vulnerability surface where untrusted data could influence command execution.
Ingestion points: User-provided parameters such as composition-id, output file names, and frame numbers in SKILL.md and transparent-videos.md.
Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within user-supplied input strings.
Capability inventory: The agent is instructed to perform shell command execution via npx as detailed in SKILL.md.
Sanitization: There are no specific instructions or mechanisms provided within the skill to sanitize or validate external user input before it is interpolated into the CLI commands.

remotion-render