The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the agent to install the @membranehq/cli package from the npm registry. This is a vendor-owned package used to facilitate secure communication with the Membrane platform.
[COMMAND_EXECUTION]: The skill uses the membrane command-line interface to perform tasks such as logging in, connecting to services, and executing API actions.
[DATA_EXFILTRATION]: The skill transfers data between the agent's environment and external endpoints (Membrane and Woovi). This is the intended functionality of the integration.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to processing data retrieved from the external Woovi API.
1. Ingestion points: External data enters the agent context via membrane action run and membrane request commands (found in SKILL.md).
2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided documentation.
3. Capability inventory: The agent has the ability to run shell commands via the CLI, perform network requests, and manage local connections.
4. Sanitization: There is no evidence of sanitization or validation applied to the data received from the external API before it is processed by the agent.

woovi