The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm and utilizes npx to execute the CLI. These are vendor-owned tools necessary for the platform's functionality.
[COMMAND_EXECUTION]: The integration operates by executing shell commands via the membrane CLI to authenticate, manage connections, and trigger actions on the Bright Security service.
[DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were found. The skill uses the Membrane proxy to handle all interactions with the Bright Security API, which centralizes authentication and minimizes the exposure of credentials in the local environment.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it retrieves data from external sources such as security scans and vulnerability issues.
Ingestion points: External data is brought into the agent context through membrane action run and membrane request commands.
Boundary markers: The skill documentation does not define specific delimiters for separating untrusted security scan data from instructions.
Capability inventory: The agent can execute various shell commands through the membrane CLI, which allows for managing infrastructure and connections.
Sanitization: There are no explicit instructions provided for the validation or sanitization of the retrieved security data before it is processed by the agent.

bright-security