The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the Membrane CLI tool from the public NPM registry to function.
Evidence: npm install -g @membranehq/cli@latest in SKILL.md.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to manage authentication, establish connections to the Freshservice API, and execute actions.
Evidence: Commands such as membrane login, membrane connection ensure, and membrane action run are used throughout SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from Freshservice, such as ticket details and notes, which are considered untrusted ingestion points.
Ingestion points: list-tickets, get-ticket, and membrane request calls in SKILL.md.
Boundary markers: No specific delimiters are used to wrap the data retrieved from the API.
Capability inventory: The skill has the ability to execute shell commands via the membrane CLI and perform authenticated network operations to Freshservice.
Sanitization: There is no explicit mention of sanitizing or filtering the content retrieved from Freshservice before it is processed by the agent.

freshservice