The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions specify the use of the yt-dlp command-line utility in a terminal to extract subtitles from YouTube videos.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external, potentially untrusted sources such as blog posts, YouTube metadata, and user-provided transcripts.
Ingestion points: Section 1 of SKILL.md details reading content via pasted text, open_post for connected channel links, and subtitle extraction.
Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from following directives embedded within the ingested source content.
Capability inventory: The skill has the ability to execute terminal commands (yt-dlp) and publish content to various social media platforms (publish).
Sanitization: No sanitization or validation steps are mentioned for the external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill employs the media_from_url tool to retrieve images and media from public HTTPS addresses provided during the session.

repurpose