The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI tool to perform operations such as listing actions, running API requests, and managing account connections.
[EXTERNAL_DOWNLOADS]: The skill documentation instructs the installation of the @membranehq/cli package from the NPM registry and the use of npx to execute vendor-specific tools.
[PROMPT_INJECTION]: The skill processes data retrieved from the LMNT API, which creates a surface for indirect prompt injection. * Ingestion points: External data from the LMNT API enters the agent context through the outputs of membrane action run and membrane request commands documented in SKILL.md. * Boundary markers: No explicit delimiters or instructions are used to separate ingested data from system instructions. * Capability inventory: The skill provides the agent with capabilities to execute CLI commands and perform proxied network requests (SKILL.md). * Sanitization: The skill does not specify any sanitization, validation, or filtering of the content retrieved from the external API before it is processed by the agent.

lmnt