The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a local Python script scripts/editor_project_export.py. This is a routine action for a file-conversion utility.
[INDIRECT_PROMPT_INJECTION]: The skill reads external editorial state from a reference file, representing a potential ingestion point for untrusted instructions.
Ingestion points: The relative file path ../../references/EDITOR_PROJECT_EXPORT.md is read during the workflow.
Boundary markers: No explicit markers or 'ignore' instructions are provided to the agent for processing the input content.
Capability inventory: The skill possesses shell execution capabilities through the Python script call.
Sanitization: No sanitization or data validation steps for the input reference file are described.

kdenlive-export