The Agent Skills Directory

[SAFE]: The skill utilizes the official @membranehq/cli package, which is the primary tool provided by the vendor for interacting with their ecosystem. All network and data operations are routed through this authenticated CLI.
[SAFE]: Credential handling is performed through the 'membrane login' flow, which ensures that sensitive tokens or API keys are managed server-side and are never exposed directly within the skill's instructions or the agent's local environment.
[SAFE]: No patterns of prompt injection, obfuscation, or unauthorized data exfiltration were found. The skill specifically instructs the user to avoid asking for API keys, adhering to the principle of least privilege.

peaka