The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external user data defined as "source material". While it lacks explicit boundary markers or sanitization for this input, the risk is negligible because the skill does not possess dangerous capabilities like command execution, network access, or file system modification. It purely generates a markdown production brief.
Ingestion points: Processes "user's source material" to define the video promise and content beats.
Boundary markers: None present.
Capability inventory: No subprocess calls, network operations, or file-writing capabilities detected.
Sanitization: None present.
[DATA_EXPOSURE]: The skill includes a production requirement to identify and replace "Privacy-sensitive material". This is a defensive best practice to ensure users do not accidentally include sensitive information in their recordings.
[NO_CODE]: The skill consists entirely of natural language instructions and markdown templates. There are no scripts, binaries, or automated command executions.

screencast-plan