The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install and use the @membranehq/cli package from the npm registry. This is a legitimate tool provided by the vendor to facilitate secure authentication and interaction with their API.
[COMMAND_EXECUTION]: The skill relies on the execution of terminal commands to function.
The agent uses membrane login, membrane connection ensure, and membrane action run to manage the integration.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from Mercado Libre, which is an external source containing user-generated content.
Ingestion points: Untrusted data enters the agent context through the outputs of marketplace actions and proxy requests (as described in SKILL.md).
Boundary markers: The skill documentation does not define specific delimiters or instructions to prevent the agent from following potential commands embedded in the retrieved marketplace data.
Capability inventory: The agent has the capability to execute shell commands via the Membrane CLI and make network requests through the Membrane proxy.
Sanitization: There is no description of sanitization, validation, or filtering of the external data before it is presented to the agent.

mercado-libre