The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This tool is the official CLI for the Membrane platform and is used to manage integrations.
[COMMAND_EXECUTION]: The instructions utilize shell commands such as membrane login and membrane action run to interact with the Bitquery API through the Membrane middleware. These are standard operations for the tool's intended purpose.
[CREDENTIALS_SAFE]: The skill explicitly instructs users to avoid hardcoding API keys or tokens, directing them to use Membrane's server-side connection management. This follows security best practices for credential handling.
[INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for blockchain data which could potentially contain adversarial content designed to influence the agent.
Ingestion points: The skill ingests untrusted blockchain data through GraphQL query responses processed by membrane action run.
Boundary markers: There are no explicit markers or delimiters defined in the instructions to separate data from instructions.
Capability inventory: The skill has the capability to execute actions on the Membrane platform and create new automated logic.
Sanitization: No explicit sanitization or filtering of the retrieved blockchain data is mentioned in the skill definition.

bitquery