network-design
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and metadata are consistent with its stated purpose of supply chain network design. The provided evaluation files and trigger sets are standard for testing intent classification and output quality.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external systems such as ERP, TMS, and customs databases. This creates a potential attack surface for indirect prompt injection if those external systems contain adversarial content.
- Ingestion points: ERP, TMS, customs databases, web search, and manual input as specified in
SKILL.md. - Boundary markers: The skill does not define specific boundary markers or instructions to ignore embedded commands in the source data.
- Capability inventory: The skill utilizes web search and integrates with enterprise systems (ERP/TMS) via MCP, providing a functional path for processed data to influence outcomes.
- Sanitization: No explicit sanitization or validation logic is defined for the external data sources.
Audit Metadata