The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the official npm registry. This is a recognized vendor tool provided by the skill author for platform interaction.
[COMMAND_EXECUTION]: Utilizes the membrane CLI for operations including authentication and action management. These commands are part of the intended integration workflow.
[CREDENTIALS_UNSAFE]: Encourages secure credential handling by using Membrane's server-side connection management rather than storing or requesting sensitive API keys directly.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection where user-supplied natural language queries are processed by the CLI.
Ingestion points: SKILL.md (parameters for the --intent and DESCRIPTION CLI arguments).
Boundary markers: No explicit delimiter markers are used in the command instructions.
Capability inventory: SKILL.md allows the agent to run and create actions using the membrane CLI.
Sanitization: Input validation and sanitization are performed by the Membrane platform backend.

icepay