The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to interact with the DATABASICS API. This includes commands for authentication (membrane login), connection management (membrane connect), and action execution (membrane action run). These commands are essential for the skill's primary function and are executed through the author's own infrastructure.
[EXTERNAL_DOWNLOADS]: Instructions are provided to install the @membranehq/cli package from the npm registry. This is a vendor-owned tool required for the skill to operate and is considered a safe dependency within the context of the skill's purpose.
[PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill accepts user-provided data to be passed to external actions.
Ingestion points: Data enters the context through the --input flag in the membrane action run command in the SKILL.md file.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands in the provided command templates.
Capability inventory: The skill has the ability to make network requests and execute actions via the Membrane CLI, as documented in the Popular actions and Proxy requests sections.
Sanitization: No explicit sanitization or validation of the input data is described in the skill instructions.
[SAFE]: The documentation contains a mismatch between the described business platform and the linked official website (databasic.io), which appears to be a documentation error rather than a malicious deception.

databasics