The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI from the official npm registry.
Evidence: npm install -g @membranehq/cli is used to provide the necessary tooling for the integration.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line utility to perform various tasks.
Evidence: Commands such as membrane login, membrane connect, and membrane action run are used to manage authentication and interact with the Jotform API.
[DATA_EXFILTRATION]: The skill facilitates the retrieval and management of data from Jotform.
Evidence: While the skill reads submissions and form data, it does so through authenticated channels and the intended Jotform API endpoints, with no evidence of unauthorized exfiltration to third-party domains.
[PROMPT_INJECTION]: The skill processes external data from Jotform submissions, which represents a potential surface for indirect prompt injection.
Ingestion points: list-form-submissions, get-submission (SKILL.md)
Boundary markers: Absent
Capability inventory: membrane action run, membrane request (SKILL.md)
Sanitization: Absent

jotform