mojo-python-interop

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill correctly documents Mojo's interoperability with Python using standard library modules such as std.python and std.os.
  • [DYNAMIC_EXECUTION]: The skill explains how to use Python.evaluate to execute Python code strings and PythonModuleBuilder to compile Mojo code into shared libraries, which are core features for language interoperability.
  • [INDIRECT_PROMPT_INJECTION]: The documentation contains a pattern for dynamic code generation that could be misused if provided with untrusted input.
  • Ingestion points: The field parameter in the sort_by_field example in SKILL.md.
  • Boundary markers: None are present in the provided code example.
  • Capability inventory: Uses Python.evaluate to execute code constructed at runtime.
  • Sanitization: None; the example uses direct string concatenation into a Python lambda expression.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:47 AM
Security Audit — agent-trust-hub — mojo-python-interop