The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the official Membrane CLI package (@membranehq/cli) from the NPM registry.
[COMMAND_EXECUTION]: The skill uses local CLI commands to manage authentication and interact with the Speakeasy API through the Membrane proxy.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests meeting transcripts and recordings from the Speakeasy platform. \n
Ingestion points: External data is retrieved via the membrane action run command as described in SKILL.md. \n
Boundary markers: The instructions do not define specific delimiters to isolate external data from instructions. \n
Capability inventory: The skill can execute CLI commands via membrane and perform network operations via membrane request. \n
Sanitization: There is no mention of sanitization or filtering for the processed records.

speakeasy