The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Recommends installing the @membranehq/cli package. This is a vendor-provided tool used to facilitate communication with the Loops.so API through the Membrane platform.
[COMMAND_EXECUTION]: Employs the membrane CLI for managing lifecycle events, such as logging in and executing predefined actions. This allows the agent to interact with external services via a structured interface.
[CREDENTIALS_UNSAFE]: The skill follows secure practices by delegating authentication to the Membrane connection manager, which avoids the need to handle sensitive API tokens or secrets within the local environment or prompt history.
[DATA_EXFILTRATION]: Accesses and processes data from Loops.so. The communication is routed through the Membrane platform, which serves as a secure proxy for API interactions.
[PROMPT_INJECTION]: Identifies an indirect prompt injection surface where external data from Loops.so enters the agent context. This is a standard risk factor for integrations that process external API content:
Ingestion points: Data enters via membrane action list and membrane action run outputs in SKILL.md.
Boundary markers: None explicitly defined in the provided instructions.
Capability inventory: Subprocess execution via the membrane CLI is available for creating and running actions.
Sanitization: Not specified; the skill relies on the agent's internal safety guardrails for handling external data.

loopsso