The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the official npm registry. This is a legitimate tool provided by the vendor to facilitate platform interactions.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform core functions including authentication (login), creating connections (connect), and executing form actions (action run). These commands are standard for the tool's integration purpose.
[PROMPT_INJECTION]: The skill provides an interface to read external data from Gravity Forms, which introduces a surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through actions such as get-form-results, list-form-entries, and get-entry in SKILL.md.
Boundary markers: The instructions do not define clear delimiters or provide instructions to the agent to ignore potentially malicious content within form entries.
Capability inventory: The agent has the capability to execute follow-up actions via membrane action run, which could include modifying data or interacting with other connected services.
Sanitization: There is no logic described to sanitize or filter the content retrieved from external form entries before processing.

gravity-forms