The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The documentation in reference.md references the official installation method for the Turso CLI using a piped shell command (curl -sSfL https://get.tur.so/install.sh | bash). This is a standard installation pattern for this well-known cloud service.
[EXTERNAL_DOWNLOADS]: The skill references the Turso installation script and links to official Turso documentation and connection endpoints (e.g., libsql://host.turso.io). These references are directed at the well-known Turso service infrastructure.
[COMMAND_EXECUTION]: The skill provides a reference for using the Turso CLI (turso db create, turso auth login, etc.), which involves executing shell commands to manage database resources.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external Turso databases via client.execute() and client.batch(), presenting a surface for indirect prompt injection if the database contains untrusted content.
Ingestion points: Query results returned as ResultSet objects in SKILL.md, examples/core.md, and examples/embedded-replicas.md.
Boundary markers: Absent; the skill does not define specific delimiters for database-sourced content.
Capability inventory: The skill enables arbitrary SQL execution (execute, batch), transaction management (transaction), and local file synchronization for replicas (sync).
Sanitization: Absent; the examples show direct mapping of database rows to application logic without explicit sanitization of the content.

api-baas-turso