spree-b2b
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill mentions default credentials (
wholesale@example.com/spree123) provided by the platform's sample data generator. These are documented as publicly known for demo purposes, and the skill includes a specific warning to never load sample data into production environments. - [INDIRECT_PROMPT_INJECTION]: The skill describes processes that handle user-supplied data, representing a surface for indirect instructions.
- Ingestion points: Member emails, invitation tokens, company names, address labels, and Purchase Order (PO) numbers (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are provided to the agent for handling these inputs.
- Capability inventory: The agent is instructed to perform API actions such as creating memberships, updating cart metadata, and managing catalogs (SKILL.md).
- Sanitization: The skill does not describe methods for sanitizing or escaping the user-provided data interpolated into these operations.
- [EXTERNAL_DOWNLOADS]: The skill references developer documentation on the
spreecommerce.orgwebsite and within the local@spree/docslibrary. These are official vendor resources for the Spree platform.
Audit Metadata