israeli-tabu-extract-decoder
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: A static detector flagged potential concealment of actions in the skill instructions. Manual review confirms these are actually safety instructions designed to prevent the AI from offering unauthorized legal advice or definitive verdicts on property titles. These instructions are protective in nature rather than malicious.
- [DATA_EXFILTRATION]: The skill explicitly states it uses no scripts and makes no network calls. No patterns for credential harvesting or data exfiltration to external domains were found.
- [EXTERNAL_DOWNLOADS]: The skill references official Israeli legislation and regulations on WikiSource (he.wikisource.org). These are trusted sources for public legal text and do not pose a security risk.
- [NO_CODE]: The skill consists entirely of Markdown instructions and reference data. There are no Python scripts, Node.js modules, or shell commands included in the package.
Audit Metadata