The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform administrative and operational tasks, such as membrane login, membrane connect, and membrane action run. These commands are standard for the Membrane platform and are used to facilitate the integration with Urlbox.io.\n- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the @membranehq/cli package from the NPM registry. This is a legitimate tool provided by the vendor for managing Membrane-based integrations.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its core functionality. \n
Ingestion points: The skill ingests untrusted data in the form of URL and HTML provided by users or external sources to generate screenshots (SKILL.md).\n
Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore potentially malicious instructions embedded within the processed web content.\n
Capability inventory: The agent has the capability to execute shell commands via the membrane CLI, including making arbitrary network requests (SKILL.md).\n
Sanitization: There is no evidence of sanitization or filtering of the input URLs or HTML code before they are passed to the screenshotting service.

urlboxio