The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process data from external, user-provided Google Docs and Sheets, which constitutes an untrusted data ingestion surface.
Ingestion points: SKILL.md describes tools that accept a <DOC_ID_OR_URL> or <SHEET_ID_OR_URL> to download external content.
Boundary markers: The provided instructions do not define clear boundaries or 'ignore' instructions for the agent when processing the content retrieved from these external sources.
Capability inventory: The skill has the capability to write files to the local file system (via --output-dir) and performs network requests to fetch data.
Sanitization: While the skill documentation mentions sanitizing output filenames based on document titles, there is no mention of sanitizing or filtering the content of the documents themselves before they are presented to the agent.
[COMMAND_EXECUTION]: The skill uses uv run to execute local Python scripts (scripts/docs.py and scripts/sheets.py) and invokes gcloud for authentication, which are standard development workflows.
[EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of content from official Google APIs (googleapis.com). These interactions target well-known services for the purpose of data ingestion.

google-docs-sheets