The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package, which is the official CLI tool belonging to the skill's author, membranedev.
[COMMAND_EXECUTION]: Utilizes the membrane command-line utility to perform integration tasks such as authentication, searching for actions, and executing API requests.
[PROMPT_INJECTION]: Evaluated for potential indirect prompt injection as the skill processes data from FireEye (alerts, events, malware details). While the skill handles external data, this is inherent to its primary purpose of managing FireEye records, and it follows security best practices by delegating credential management to the Membrane platform.
Ingestion points: FireEye API responses retrieved via membrane action run and membrane request (described in SKILL.md).
Boundary markers: Not explicitly defined in the instructions.
Capability inventory: Command execution via the vendor CLI (documented in SKILL.md).
Sanitization: Authentication and request handling are managed by the Membrane platform abstraction.

fireeye