The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the official NPM registry. This is the standard tool provided by the vendor (membranedev) to facilitate the integration.
[COMMAND_EXECUTION]: The skill instructions involve executing membrane CLI commands to perform authentication, search for actions, and manage project data. These commands are scoped to the intended functionality of the integration.
[CREDENTIALS_UNSAFE]: The skill does not contain hardcoded secrets. It explicitly follows best practices by directing the agent to use server-side connections and never prompts the user for raw API keys or tokens.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it retrieves and processes data from the external ProProfs Project service.
Ingestion points: Project data and action outputs retrieved via membrane action run (SKILL.md).
Boundary markers: Absent; there are no specific markers instructing the agent to ignore instructions embedded in retrieved data.
Capability inventory: Shell command execution via the membrane CLI and network access to the vendor's platform.
Sanitization: Not explicitly specified in the skill prompt; however, the data is intended for project management tasks.

proprofs-project