The Agent Skills Directory

[SAFE]: The skill implements a standard workflow for interacting with Google Workspace tools to update a sales pipeline spreadsheet. It uses specific, expected CLI tools for Google Drive and Sheets functionality.\n- [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection by reading external data from a Google Sheet. This is a common characteristic of data-processing skills and is mitigated by the skill's specific task focus.\n
Ingestion points: SKILL.md (Step 2 reads data from the 'Pipeline' sheet using the gws sheets +read command).\n
Boundary markers: Absent; there are no instructions to the agent to distinguish between its commands and the spreadsheet data.\n
Capability inventory: The skill utilizes gws sheets +append and gws drive files list capabilities.\n
Sanitization: Absent; the skill does not explicitly sanitize the data read from the spreadsheet before processing.

recipe-log-deal-update