The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (@membranehq/cli) globally via npm. This is the official command-line tool for the Membrane platform, provided by the skill author, and is necessary for the skill's operation.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to interact with external APIs. Commands such as membrane action run and membrane request are used to manage Dope.security data and automate workflows, which is the primary purpose of the skill.
[PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it processes untrusted data from the Dope.security API (such as Events, Users, and Alerts).
Ingestion points: Data enters the agent context through CLI outputs from membrane action run and membrane request in SKILL.md.
Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between data and potential instructions embedded in the API responses.
Capability inventory: The skill allows for network operations and shell command execution via the membrane CLI.
Sanitization: No explicit sanitization or validation of the retrieved API data is mentioned in the setup instructions.

dopesecurity