uspto-database
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of standard Python packages (
requests,pandas,matplotlib,google-cloud-bigquery) and connects to well-known data services includingapi.patentsview.organd Google Cloud BigQuery. These operations are consistent with the skill's stated purpose of retrieving patent metadata. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data (patent titles, abstracts, and claims) from the USPTO and Google Patents databases. This introduces a vulnerability surface where malicious instructions could theoretically be embedded in patent records to influence the agent's behavior during processing.
- Ingestion points: Data enters the agent's context through
requests.postcalls to the PatentsView API and BigQuery queries inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill uses
requestsfor network access andmatplotlib/pathlibfor file system writes (saving charts and caching JSON). - Sanitization: The provided code snippets perform data frame manipulation and plotting but do not include explicit sanitization or filtering of the text content fetched from the APIs.
Audit Metadata