The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Google Sheets which could contain malicious instructions.
Ingestion points: The google_sheets_values_get tool is used to read spreadsheet data (SKILL.md).
Boundary markers: No explicit prompt boundary markers or "ignore instructions" directives are specified for the ingested spreadsheet data.
Capability inventory: The skill has the ability to write to spreadsheets using google_sheets_values_update and google_sheets_values_batch_update (SKILL.md).
Sanitization: No specific sanitization or filtering of the read data is mentioned before it is processed by the agent.
[SAFE]: The skill references official vendor documentation and integration pages at app.hyperfx.ai, which is consistent with the skill author hyperfx-ai.

google-sheets