The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI to execute various tasks such as searching for connectors, connecting accounts, and running actions against the AlertOps API.
[EXTERNAL_DOWNLOADS]: The skill recommends the global installation of @membranehq/cli via npm. This is the official tool provided by the vendor (membranedev) and is a standard requirement for this skill's functionality.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from AlertOps (such as incidents, logs, and reports) that could be controlled by external actors.
Ingestion points: Data enters the agent context through the output of commands like membrane action run and membrane request as described in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are used when the agent processes AlertOps data.
Capability inventory: The skill utilizes shell command execution via the membrane CLI, which allows for reading and writing data to the AlertOps platform.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from AlertOps before it is processed by the agent.

alertops