The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from the HeySummit API (e.g., attendee details, talk descriptions) which could contain malicious instructions.
Ingestion points: HeySummit API via list-talks, get-attendee, and other read actions.
Boundary markers: None identified in the provided instructions.
Capability inventory: Execution of shell commands via the membrane CLI, including creating and running new actions.
Sanitization: No explicit sanitization of external content is mentioned.
[EXTERNAL_DOWNLOADS]: The instructions include a command to install @membranehq/cli from the official npm registry. This is a vendor-owned resource used to facilitate the integration.
[COMMAND_EXECUTION]: The skill utilizes shell commands through the membrane CLI to manage connections and execute actions. These commands are part of the core functionality of the skill.

heysummit