israeli-heritage-explorer

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves metadata and images from the National Library of Israel's API (api.nli.org.il), which is a well-known and legitimate cultural repository.
  • [COMMAND_EXECUTION]: The skill includes a Python script (scripts/nli-search-example.py) that performs API requests using the standard library; it contains no dangerous shell commands or dynamic execution logic.
  • [CREDENTIALS_UNSAFE]: API keys are managed via environment variables as per the instructions and script, adhering to secure development practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the NLI API (Ingestion: API search results). While it lacks boundary markers and sanitization for this data, it also lacks the capabilities (like system commands or file writing) required to weaponize an indirect prompt injection attack.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 03:57 PM
Security Audit — agent-trust-hub — israeli-heritage-explorer