The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from external spreadsheets.
Ingestion points: Spreadsheet data is read via the read_values method in scripts/sheets_manager.rb.
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the retrieved cell data.
Capability inventory: The skill allows for significant modifications (writing, appending, clearing) and sheet management, and shares permissions with other high-privilege Google services.
Sanitization: No validation or filtering is applied to the data fetched from spreadsheets before it is provided to the agent's context.
[EXTERNAL_DOWNLOADS]: The skill documentation lists several official Google API gems as requirements.
Trusted Source: Dependencies such as google-apis-sheets_v4 and googleauth are official, well-known libraries maintained by Google. These references are considered safe and do not escalate the security verdict.

google-sheets