european-patent-claims-review
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and metadata are consistent with its stated purpose of providing professional patent auditing services following European Patent Office (EPO) guidelines.
- [SAFE]: All external references and Model Context Protocol (MCP) service links point to the vendor's official domains (patsnap.com and zhihuiya.com, the developer's brand name in China). These are recognized as legitimate vendor resources.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided patent documents and claims.
- Ingestion points: User-uploaded patent files, claim sets, or specification drafts (SKILL.md).
- Boundary markers: None explicitly defined for untrusted content.
- Capability inventory: The skill performs text analysis, classification, and reporting; it does not contain capabilities for arbitrary command execution or network exfiltration.
- Sanitization: Standard LLM guardrails are assumed as the skill does not implement custom sanitization. The risk is considered minimal and inherent to the skill's primary function.
Audit Metadata