The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from Google Sheets, which acts as an untrusted external source.
Ingestion points: The skill retrieves spreadsheet content using the gog sheets get command as described in SKILL.md.
Boundary markers: The documentation explicitly recommends the use of the --wrap-untrusted flag to help the agent identify and delimit external content.
Capability inventory: The tool possesses significant capabilities to modify or delete data, including update, append, batch-update, and delete-tab commands listed in SKILL.md.
Sanitization: The recommended --wrap-untrusted flag serves as a sanitization mechanism to prevent the agent from misinterpreting spreadsheet content as direct instructions.

gog-sheets