uspto-database
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external USPTO APIs, which could theoretically contain instructions intended to influence the agent's behavior.
- Ingestion points: External data enters the context from multiple API endpoints including
search.patentsview.org,tsdrapi.uspto.gov, andassignment-api.uspto.gov(identified in SKILL.md). - Boundary markers: The instructions do not specify any boundary markers or delimiters (like XML tags or markdown blocks) to isolate external content from agent instructions.
- Capability inventory: The skill includes scripts for network requests (
requests.get/post) and analysis logic capable of reading and interpreting patent text, claims, and trademark statuses. - Sanitization: There is no evidence of content sanitization or validation to filter out potential prompt injection strings from the API responses before they are presented to the agent.
Audit Metadata