sendowl
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
@membranehq/clipackage from the official NPM registry. This is a legitimate tool provided by the author (membrane) for managing integrations. - [COMMAND_EXECUTION]: Uses the
membranecommand-line utility for authentication, searching actions, and executing API requests. This is the intended behavior of the skill and follows standard development workflows for this platform. - [DATA_EXFILTRATION]: Employs a proxy system (
membrane request) to communicate with the SendOwl API. This allows the platform to manage sensitive authentication headers and credential refreshes server-side, preventing the need to store or handle raw API keys in the local environment. - [PROMPT_INJECTION]: The skill is designed to process data from the SendOwl API (such as orders and customer records) which constitutes an external data ingestion surface. 1. Ingestion points: Data returned from
membrane action runormembrane request. 2. Boundary markers: None explicitly mentioned in the instructions. 3. Capability inventory: The skill can execute platform actions and make requests to the SendOwl API via the CLI. 4. Sanitization: Not specified in the markdown instructions. This represents a standard surface for indirect prompt injection common to API integration skills.
Audit Metadata