struktura-wyroku-pl
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill is designed for the structural analysis of legal documents and adheres to its stated purpose. No malicious commands, persistence mechanisms, or obfuscated instructions were detected.
- [PROMPT_INJECTION]: The skill ingests external data (court rulings) via the Read tool or manual input (Workflow Step 1), which constitutes a surface for indirect prompt injection. However, the instructions mandate extractive summarization (quoting source sentences verbatim), which mitigates the risk of the agent following embedded instructions. Boundary markers and sanitization processes are not defined, but capabilities are restricted to reading.
- [EXTERNAL_DOWNLOADS]: The skill includes a reference to the OpenNyAI GitHub repository for attribution purposes. This is a documentation link and does not involve automated script execution or package installation.
Audit Metadata