The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package via npm. This is a legitimate developer utility provided by the skill author for managing integrations.
[COMMAND_EXECUTION]: The instructions guide the agent to use the membrane CLI to perform authentication, search for connectors, and execute actions. These are standard operations for interacting with the Membrane platform.
[DATA_EXFILTRATION]: No unauthorized data transfer was detected. The skill emphasizes using Membrane's server-side credential management to avoid handling sensitive API keys locally.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Bland AI, such as call transcripts and record details, which represents a potential injection surface.
Ingestion points: Data enters the agent's context through membrane action run and membrane request output.
Boundary markers: None are explicitly defined in the provided markdown instructions.
Capability inventory: The skill uses the CLI for network requests and action execution.
Sanitization: The instructions do not specify sanitization for the data retrieved from the API.
[SAFE]: The skill correctly directs users to official resources and uses secure-by-default practices for credential management through a trusted proxy service.

bland-ai