legal-patent-search
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill implements secure credential management by instructing the agent to store the KIPRIS API key in a dedicated environment file (
moai-credentials.env) within the restricted plugin data directory. This adheres to security best practices for secret isolation. - [EXTERNAL_DOWNLOADS]: The skill makes legitimate requests to the KIPRIS Plus Open API (
plus.kipris.or.kr). This is a well-known service for intellectual property data, and the interaction is limited to standard GET requests for search results. - [INDIRECT_PROMPT_INJECTION]: The skill processes external XML data from patent records.
- Ingestion points:
SKILL.md(Step 3: KIPRIS API search). - Boundary markers: The skill does not explicitly define delimiters for summarized claim text.
- Capability inventory: The skill's functionality is limited to data retrieval and report formatting; it does not execute system commands or perform sensitive file writes based on the ingested content.
- Sanitization: Not explicitly mentioned, but the risk is mitigated by the highly structured nature of the bibliographic data and the limited capabilities of the skill.
- [COMMAND_EXECUTION]: No suspicious command execution or shell spawning was detected. All workflow steps are limited to standard API interactions and text processing.
Audit Metadata