israeli-amuta-compliance
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing two Model Context Protocol (MCP) servers to enhance its lookup capabilities. One is a package provided by the skill author (@skills-il/israel-amutot-mcp) and the other is an established Israeli open-data service (budgetkey at next.obudget.org). Both are used to fetch public registry data.
- [COMMAND_EXECUTION]: The skill includes a local Python utility,
scripts/band_check.py, used to determine an organization's governance requirements and fee tiers based on financial turnover. The script uses only the Python standard library and does not perform any network operations or access sensitive local files. - [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to process external data retrieved through the recommended MCP tools (file:
SKILL.md). - Ingestion points: Data returned by registry lookup tools, including entity status and financial history.
- Boundary markers: The instructions do not define specific delimiters for separating tool output from the system prompt, although the resulting data is formatted into structured reports.
- Capability inventory: The skill's primary function is informational reporting; it does not possess capabilities to write files or initiate unauthorized network connections based on external input.
- Sanitization: There is no specific documentation regarding the sanitization or escaping of external content before it is processed by the agent.
Audit Metadata