The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external spreadsheets, which provides a surface for indirect prompt injection attacks.
Ingestion points: The skill uses methods like sheets.values.get, sheets.get, and sheets.getByDataFilter to retrieve content from external Google Sheets (SKILL.md).
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the retrieved spreadsheet content as untrusted or separate from instructions.
Capability inventory: The skill has the ability to create and update spreadsheets (sheets.batchUpdate, sheets.create) and executes operations via the gws CLI (SKILL.md).
Sanitization: There is no mention of sanitization, filtering, or validation of the data retrieved from the spreadsheets before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references official Google Workspace developer documentation for API guidance.
Evidence: The skill provides links to developers.google.com for field masks and metadata guidelines (SKILL.md).

gws-sheets