The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill requires the installation of the @membranehq/cli package from the NPM registry to facilitate Snowflake operations. This is a vendor-owned resource.\n- [COMMAND_EXECUTION]: The skill relies on shell commands executed via the membrane CLI to manage connections, handle authentication, and run database actions.\n- [DYNAMIC_EXECUTION]: The membrane action create command dynamically generates integration logic on the vendor platform based on natural language descriptions provided to the agent.\n- [INDIRECT_PROMPT_INJECTION]: Results retrieved from Snowflake queries constitute a surface for indirect prompt injection where adversarial data in the database could influence agent behavior.\n
Ingestion points: Data returned from the Snowflake database via the membrane action run command (SKILL.md).\n
Boundary markers: No explicit delimiters or instructions to ignore nested commands are provided in the command templates.\n
Capability inventory: The agent has access to shell command execution via the membrane CLI (SKILL.md).\n
Sanitization: No sanitization or validation of retrieved database content is defined in the instructions.

snowflake