screen-cross-border-patent-risk-ip
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill references official Patsnap MCP tools and domains (open.patsnap.com), which align with the identified authorship and intended use-case.- [INDIRECT_PROMPT_INJECTION]: The skill ingests technical descriptions and product pages, which represents a potential attack surface for indirect prompt injection. This is considered a safe finding due to the primary purpose of the skill and the structured data normalization workflow. Ingestion points: Product images and technical descriptions acquired in Phase 1. Boundary markers: Instructions do not explicitly require the use of delimiters for external content. Capability inventory: Access is restricted to Patsnap MCP servers; no dangerous system-level capabilities are exposed. Sanitization: The workflow requires the agent to extract and describe specific features (Phase 1, Steps 2-3) before performing searches, which acts as a normalization process.
Audit Metadata