ecommerce-patent-family-data
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API (PatSnap), which represents an ingestion surface for untrusted content. However, the data is treated as informational and used for structured display, posing minimal risk. Mandatory Evidence: Ingestion points: scripts/patent_family_data.py (API response parsing); Capability inventory: HTTPS POST requests to the vendor API, writing JSON and metadata files to the local filesystem; Boundary markers: None; Sanitization: Data is handled through JSON serialization and parsing.
- [PERSISTENCE]: The accompanying Python script implements a 24-hour local cache and maintains session-level index and metadata files in a vendor-specific directory within the project or home folder. This persistence is a functional feature for data management and performance, not a malicious persistence mechanism.
Audit Metadata