The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads the @membranehq/cli package from the public NPM registry using npx. This is the official tool provided by the skill author to facilitate the integration.
[COMMAND_EXECUTION]: Shell commands are used extensively to interact with the Membrane platform, including logging in, managing connections, and executing actions on external APIs.
[DATA_EXFILTRATION]: The skill transmits connection parameters, action inputs (such as message text or task details), and authentication tokens to https://api.getmembrane.com. This is the documented and intended operational flow for the Membrane service.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes data from external, untrusted sources such as Slack messages or Jira tickets.
Ingestion points: Data enters the agent's context through the output of npx @membranehq/cli action run (SKILL.md).
Boundary markers: No explicit delimiters or instructions are used to separate external data from the agent's core instructions.
Capability inventory: The agent can execute shell commands via npx and make network requests to the Membrane API (SKILL.md).
Sanitization: The instructions do not describe any mechanisms for validating or escaping content retrieved from external apps before it is processed by the agent.

integrate-anything