The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry. This is an official command-line tool provided by the vendor for interacting with their platform.
[COMMAND_EXECUTION]: The skill operates by executing shell commands via the membrane CLI to manage connections, search for actions, and execute tests.
[PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection (Category 8) when handling user-supplied input.
Ingestion points: Untrusted data enters the agent context through the --intent and --input parameters described in SKILL.md.
Boundary markers: None. The instructions do not define delimiters or provide warnings to the agent to ignore instructions embedded within the user-provided intent or JSON data.
Capability inventory: The skill has the capability to run shell commands (membrane action run) and create new executable logic (membrane action create) as documented in SKILL.md.
Sanitization: There is no mention of sanitizing, escaping, or validating the user-provided strings before they are interpolated into the shell command strings.

rainforest-qa