uspto-database
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves patent records and metadata from the official PatentsView API (
api.patentsview.org) and Google Patents Public Data on BigQuery. These are well-known and reputable services for accessing public patent information. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data (patent titles and abstracts) that could theoretically contain malicious instructions.
- Ingestion points: External data is ingested via
requests.postcalls to the PatentsView API inSKILL.md. - Boundary markers: The code examples do not implement specific boundary delimiters or safety instructions to the agent to ignore potentially malicious content within the retrieved patent text.
- Capability inventory: The skill includes file writing capabilities via
matplotlib(plt.savefig) and data processing throughpandasandrequests. - Sanitization: There is no explicit sanitization or filtering of the retrieved API data before it is processed by the agent.
Audit Metadata