israeli-fact-checker

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements strong safety measures to prevent the generation of fabricated information. It explicitly instructs the agent to use a specific verdict ('אין מספיק נתונים') if official data cannot be retrieved, rather than guessing or estimating.
  • [SAFE]: All external sources referenced are official Israeli government domains (e.g., cbs.gov.il, boi.org.il, data.gov.il) or well-known, trusted organizations (e.g., The Whistle/Globes, IFCN, FakeReporter). These are appropriate for the skill's stated purpose of public interest verification.
  • [SAFE]: The included Python script (scripts/verdict_template.py) is a benign utility that provides templates and routing logic. It does not perform any network operations, file system modifications, or dynamic code execution.
  • [SAFE]: The skill follows least-privilege principles by recommending specific MCP tools for different data categories (e.g., nadlan for real estate, boi-exchange for currency) rather than requesting broad, unmonitored access.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 06:53 PM
Security Audit — agent-trust-hub — israeli-fact-checker