The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to check for, install, and run Python-based transcript extraction tools. Specifically, it uses pip install to manage dependencies and python3 to execute the extract-transcript.py script.
[EXTERNAL_DOWNLOADS]: The skill downloads the youtube-transcript-api package from the official Python Package Index (PyPI). This is a well-known package used for its stated purpose.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it processes untrusted text data from external YouTube transcripts.
Ingestion points: Transcripts are fetched from YouTube in scripts/extract-transcript.py and subsequently read into the AI's context for summarization as described in SKILL.md.
Boundary markers: The summarization instructions do not include specific delimiters or instructions to ignore potential commands embedded within the transcript text.
Capability inventory: The skill possesses the ability to execute shell commands (for setup) and write to the local file system (saving transcripts to /tmp/).
Sanitization: The skill does not implement filtering or sanitization of the transcript content before presenting it to the AI model for analysis.

youtube-summarizer