The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation and usage of the @membranehq/cli package from the npm registry. This is a verified resource belonging to the author's organization for managing Membrane integrations.
[COMMAND_EXECUTION]: The skill relies on executing various shell commands through the membrane CLI to authenticate users, manage connections, and interact with the Vectorized.io API. These commands are part of the skill's intended primary functionality.
[PROMPT_INJECTION]: The skill processes streaming data and records from Vectorized.io, which presents an indirect prompt injection surface where untrusted external data could potentially contain malicious instructions. Evidence: Ingestion points (CLI command outputs in SKILL.md); Boundary markers (None); Capability inventory (Command execution via Membrane CLI); Sanitization (None). This is documented as a standard risk factor for data-intensive integrations.

vectorizedio