The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the @membranehq/cli package globally via npm. This package is the official command-line tool for the Membrane platform, which is the skill's authoring environment.
[COMMAND_EXECUTION]: The integration logic relies on executing shell commands using the membrane CLI, including login, connect, action run, and request to manage the interaction with the LinearB API.
[DATA_EXFILTRATION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from LinearB.
Ingestion points: Data is retrieved from the LinearB API via membrane action run and membrane request as described in SKILL.md.
Boundary markers: There are no specific delimiters or instructions provided to the agent to distinguish between its own logic and potentially malicious instructions embedded in the retrieved data.
Capability inventory: The skill allows for network writes to the LinearB API (e.g., create-incident, delete-user, update-team) via the membrane action run and membrane request commands.
Sanitization: No sanitization or validation of the external API content is specified before the data is processed by the agent.

linearb