The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the official Membrane CLI (@membranehq/cli) from the npm registry to facilitate platform integration.
[COMMAND_EXECUTION]: The skill uses the membrane command-line utility for authentication, connecting to CTO.ai, and executing automation workflows.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes content from external actions.
Ingestion points: Data returned from membrane action run and descriptions retrieved via membrane action list (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between system instructions and data returned from external tools.
Capability inventory: The agent can execute shell commands through the CLI and create new actions based on natural language descriptions (SKILL.md).
Sanitization: The skill does not define specific methods for validating or sanitizing external data before it is incorporated into the agent's reasoning context.

ctoai