blink
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: All network requests are directed to the official Blink GraphQL API and WebSocket endpoints. Sensitive credentials are resolved from the local environment or profile and are used only for authentication with the intended service.\n- [EXTERNAL_DOWNLOADS]: The skill relies entirely on Node.js built-in modules and its own distributed scripts; no external packages or remote code are downloaded at runtime.\n- [COMMAND_EXECUTION]: Filesystem access is used appropriately for reading user configuration and writing generated QR code PNG files to the system temporary directory.\n- [PROMPT_INJECTION]: The skill's instructions and metadata are focused on operational wallet tasks and do not contain patterns attempting to override agent safety guidelines or system prompts.
Audit Metadata