epo-patent-search
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill integrates with official and well-known services (EPO and Google Cloud) to perform its stated functions.
- [CREDENTIALS_UNSAFE]: The instructions correctly guide users to set up their environment using variables for sensitive project IDs and API keys, which prevents credential exposure in the source code.
- [PROMPT_INJECTION]: The skill retrieves and processes external patent data (titles, abstracts, and claims) from APIs. This constitutes an indirect prompt injection surface where malicious data could potentially influence the agent. However, this is an inherent aspect of patent research tools and is handled by the model's standard safety layers. Ingestion points: Patent results from EPO OPS and BigQuery; Boundary markers: None specified in the instructions; Capability inventory: Access to Bash, Read, and Write tools; Sanitization: Relies on platform-level LLM guardrails.
Audit Metadata