glasses-ui
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill integrates with the
@evenrealities/even_hub_sdkpackage to manage the hardware display and communication, which is the official library provided by the vendor. - [INDIRECT_PROMPT_INJECTION]: The skill uses a placeholder to ingest user-supplied tasks, which are processed in an environment with significant system access tools.
- Ingestion points: User input is accepted via the
$ARGUMENTStag at the end of theSKILL.mdfile. - Boundary markers: There are no explicit delimiters or instructions provided to the model to ignore or sanitize embedded instructions within the user-supplied task.
- Capability inventory: The skill is configured with access to powerful tools including
Bash,Write,Edit,Read,Grep, andGlob. - Sanitization: The skill does not implement input validation or escaping for the interpolated user content.
Audit Metadata