The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package via npm and utilizes npx to execute commands. These are official tools from the vendor used for platform interaction.
[COMMAND_EXECUTION]: The instructions involve running shell commands via the membrane CLI to manage authentication, service connections, and Memsource actions.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests and processes data from external Memsource actions.
Ingestion points: External data is retrieved via membrane action run and membrane action list (SKILL.md).
Boundary markers: The documentation does not specify the use of delimiters or markers to isolate external data from the system prompt.
Capability inventory: The skill uses the membrane CLI to execute various shell-based actions and workflow management tasks (SKILL.md).
Sanitization: No explicit content filtering or sanitization of ingested data is described in the skill files.

memsource