The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from npm. This is the official command-line utility for the Membrane platform and is considered a safe, vendor-owned resource.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI for managing service authentication (login), discovery (search), and interaction (connect, action run). These commands are standard for the tool's intended use and do not exhibit suspicious behavior.
[PROMPT_INJECTION]: The skill retrieves records from Airtable, creating a surface for indirect prompt injection if those records contain instructions that influence the agent's behavior.
Ingestion points: Airtable records and schema data retrieved via list-records, get-record, and get-base-schema tools.
Boundary markers: The skill does not provide specific instructions or delimiters to isolate untrusted data from the system prompt.
Capability inventory: The skill can modify Airtable data through create-records, update-records, and delete-records actions.
Sanitization: No explicit sanitization or content validation is performed on the data fetched from the Airtable API before processing.

airtable