ce-auth
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation and logo assets from
commercengine.io,github.com/commercengine, andtarkai.com. These are legitimate resources associated with the vendor's services and infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill documentation includes examples for fetching external data such as user profiles and product catalogs, which introduces a surface for indirect prompt injection.
- Ingestion points: Data is fetched via
sdk.auth.getUserDetailsandpublic()catalog reads inSKILL.md. - Boundary markers: None explicitly defined in the markdown snippets.
- Capability inventory: The SDK allows for user session management, profile updates, and cart operations.
- Sanitization: Not specified in the instruction snippets; expected to be managed by the SDK implementation.
Audit Metadata