The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions include installing the @membranehq/cli package globally via npm. This is the official command-line interface provided by the vendor for managing integrations and authentication.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform various operations, such as logging in, connecting to services, and executing actions. These are standard operations for the intended functionality of the skill.
[PROMPT_INJECTION]: The skill processes external data from Salesforce DMP, creating a surface for indirect prompt injection. The agent should be aware that data retrieved from the API could potentially contain instructions meant to influence its behavior.
Ingestion points: Data returned from membrane action run and membrane request subcommands.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill.
Capability inventory: The skill uses the membrane CLI to read data and perform actions within the Salesforce DMP environment.
Sanitization: No explicit data sanitization or validation steps are defined within the skill instructions.

salesforce-dmp