create-patent-landscape-overview-ip
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external patent databases and human-provided CSV files to generate a scientific HTML report. This presents a surface for potential indirect prompt injection. Ingestion points: Data is retrieved via MCP tools and a human-tagged file (tagged_pool.csv). Boundary markers: The skill explicitly instructs the agent to use escaped user/database text and allowlisted links in the HTML report blueprint. Capability inventory: The skill possesses capabilities for file system operations and invoking external MCP tools. Sanitization: Explicit instructions are provided to escape external content during report generation to mitigate potential injection risks.
- [EXTERNAL_DOWNLOADS]: The skill references official Patsnap MCP services hosted on open.patsnap.com for patent search and analysis capabilities. These references are vendor-specific and necessary for the skill's primary functionality.
Audit Metadata