webwright-legal-pl
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the setup of the Webwright framework by cloning from the official Microsoft GitHub repository, which is a trusted and well-known source for development tools.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external legal portals (e.g., eur-lex.europa.eu and sn.pl). While this creates a potential surface for indirect prompt injection from scraped content, the risk is minimal given the official nature of the sources and the skill's primary function as a research tool.
- [DYNAMIC_EXECUTION]: The skill utilizes an agentic workflow where Python scripts are generated and executed to handle specific website structures, a standard pattern for the Webwright framework that is well-defined within the skill's instructions.
Audit Metadata