Cross-Border E-Commerce Specialist
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions and configuration metadata. No executable scripts (.sh, .py, .js), binaries, or active command-line instructions were found.
- [NO_CODE]: There are no programming logic or automation scripts included. The skill serves as a purely behavioral and knowledge-based prompt for the AI agent.
- [INDIRECT_PROMPT_INJECTION]: The instructions suggest the agent perform 'review mining' and 'competitor analysis' on external data. While this introduces a theoretical surface for processing untrusted data, the skill itself provides no tools or automated methods to ingest this data, and the behavior is central to the legitimate e-commerce use case.
Audit Metadata