israeli-real-estate

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the review of Israeli rental contracts provided by the user (Example 3), which serves as a data ingestion surface.
  • Ingestion Point: User-provided contract text supplied to the agent for review in Example 3.
  • Boundary Markers: The skill does not explicitly instruct the agent to ignore or delimit instructions that might be embedded within the provided contract content.
  • Capability Inventory: The skill is designed for information retrieval and tax calculation; it does not possess file-writing or network exfiltration capabilities in its bundled scripts.
  • Sanitization: There is no evidence of sanitization or filtering applied to the user-supplied contract text before processing.
  • [COMMAND_EXECUTION]: The skill includes a Python script (scripts/calculate_mas_rechisha.py) to compute purchase tax. The script is self-contained, uses only standard libraries (argparse, json, sys), and performs purely mathematical operations based on local constants.
  • [SAFE]: The skill references several Israeli government domains (gov.il, nadlan.gov.il, justice.gov.il) and well-known local legal resources (kolzchut.org.il, wikisource.org) for data sourcing. These are appropriate and authoritative sources for the skill's primary function. References to MCP servers on agentskills.co.il correspond to the skill author's infrastructure and appear benign.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 10:16 AM