builtwith
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (
@membranehq/cli) from the npm registry. This is a standard installation of the vendor's official command-line tool. - [INDIRECT_PROMPT_INJECTION]: The skill interacts with the BuiltWith API to retrieve website technology profiles, which constitutes an external data ingestion surface.
- Ingestion points: External data enters the agent context via the
membrane action runandmembrane requestcommands documented in SKILL.md. - Boundary markers: The instructions do not specify explicit delimiters for the external data, relying on standard CLI output handling.
- Capability inventory: The skill enables the agent to execute actions and make proxied HTTP requests through the Membrane platform.
- Sanitization: The skill leverages Membrane's managed infrastructure for authentication and request proxying, which provides a layer of validation for API interactions.
Audit Metadata