torob
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions guide the user to install a package using uvx, which is a tool from a well-known service provider. This package is an external dependency required for the skill tools to function.
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes untrusted data from the Torob website. (1) Ingestion points: Data is retrieved from product search and price listings via tools like tb_search and tb_product. (2) Boundary markers: The instructions do not specify boundary markers or delimiters to isolate external data from system instructions. (3) Capability inventory: The skill is described as read-only and returns product data to the agent context but lacks explicit shell or file-write capabilities. (4) Sanitization: There is no evidence of sanitization or filtering of external data before it is presented to the agent.
Audit Metadata