The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted video files which are sent to the Gemini API. Videos could contain audio or visual instructions designed to manipulate the generated summary.
Ingestion points: scripts/summarize_videos.py scans for and reads all *.mp4 files in the target directory.
Boundary markers: None present. The LLM is instructed to analyze the video content directly without explicit delimiters or warnings to ignore embedded instructions.
Capability inventory: The skill writes Markdown files to the local file system and performs network operations to the Google Gemini API.
Sanitization: No sanitization is performed on the output generated by the LLM before it is written to disk as a .md file.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the google-genai Python package. This is a well-known library provided by a recognized technology company.
[COMMAND_EXECUTION]: The skill operates by executing Python scripts that perform recursive file system scans, local file writes, and network requests to external API services.

video-summarizer