The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions include the global installation of the @membranehq/cli npm package, which is necessary for the agent to communicate with the Membrane platform and the Parma API. This package is provided by the skill's vendor.
[COMMAND_EXECUTION]: The skill executes multiple commands using the membrane CLI tool, including logging in, searching for connectors, and running specific API actions. These operations are standard for the skill's stated purpose.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it allows user-provided data to be interpolated into CLI command arguments and API request parameters.
Ingestion points: Untrusted data enters the agent context through the --input flag in membrane action run and via query/path parameters in membrane request as documented in SKILL.md.
Boundary markers: The skill does not define specific delimiters or warnings to prevent the agent from interpreting instructions embedded within these data fields.
Capability inventory: The skill has the capability to perform network requests and execute platform actions through the membrane CLI.
Sanitization: The skill instructions do not specify any validation or sanitization routines for external data before it is passed to the CLI.

parma