skills/rafaelgrasa/skills/python-sdk/Gen Agent Trust Hub

python-sdk

Warn

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The documentation in references/tool-builder.md provides an example implementation of a calculator tool that uses the Python eval() function to process input from tool arguments (call.args['expression']). This is a dangerous coding pattern that allows for arbitrary command and code execution within the environment where the SDK is running if the input is not strictly validated.\n- [REMOTE_CODE_EXECUTION]: By recommending the use of eval() on strings provided via tool calls (which are often generated by AI models), the skill introduces a vulnerability surface where malicious expressions could execute arbitrary Python code.\n- [EXTERNAL_DOWNLOADS]: The skill configures and instructs the installation of the inferencesh Python package and its dependencies (such as requests, aiohttp, fastapi, and tqdm) from the public Python Package Index (PyPI).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 11:26 PM