The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using npx convex run and npx convex import to manage database records.
[EXTERNAL_DOWNLOADS]: The skill relies on the convex package executed via npx. As this is a resource provided by the vendor, it is considered a functional requirement.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data sources (CSV and JSON files) for database imports, which constitutes an ingestion surface for untrusted content.
Ingestion points: External CSV and JSON datasets provided by the user or project files.
Boundary markers: The instructions do not define specific delimiters or headers to prevent the agent from interpreting data content as instructions.
Capability inventory: The skill has the capability to execute shell commands (npx).
Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the data files before processing or importing them.

seed