The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane command-line interface from the public NPM registry using npm install -g @membranehq/cli@latest. This is a standard installation of a tool from a well-known service associated with the skill's author.
[COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands via the membrane CLI to manage logins, connections, and API actions. These commands interact with the vendor's cloud infrastructure to perform data operations.
[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests and processes professional profiles and company data from People Data Labs.
Ingestion points: Data returned from membrane action run and membrane action list is interpolated into the agent's context.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the retrieved data.
Capability inventory: The agent has the ability to execute shell commands (membrane CLI) and potentially perform network operations through them.
Sanitization: There is no evidence of automated filtering or sanitization of the external data before it is presented to the agent.

people-data-labs