The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill interacts with external Mailjet data, such as contact lists and email messages, which could contain adversarial instructions intended to manipulate agent behavior.
Ingestion points: Data is fetched through membrane action run and membrane request commands as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions to isolate untrusted data.
Capability inventory: The skill allows for sending emails and managing contact lists, which could be abused if an injection is successful.
Sanitization: No data sanitization or validation logic is explicitly defined for external content.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package, the official command-line tool for the Membrane platform, from the npm registry.
[COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands for authentication, connection setup, and performing actions within the Mailjet environment.

mailjet