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

python-sdk

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the inferencesh library and its optional dependencies (such as async support) from the official Python Package Index (PyPI).
  • [COMMAND_EXECUTION]: The skill configuration explicitly allows the execution of pip and python commands via the system shell, which is necessary for the installation of the SDK and the execution of the provided code examples.
  • [DATA_EXFILTRATION]: The documentation provides instructions and examples for uploading local files (such as images and PDFs) to the inference.sh cloud infrastructure and configuring webhook tools to transmit data to external services like Slack and GitHub.
  • [REMOTE_CODE_EXECUTION]: The references/tool-builder.md file contains a code example for a calculator tool that utilizes the eval() function to process mathematical expressions. While presented as a functional example for tool developers, this pattern involves the dynamic execution of code derived from model-generated arguments.
  • [CREDENTIALS_UNSAFE]: The skill provides guidance on authentication, correctly recommending the use of environment variables (INFERENCE_API_KEY) for secret management while providing generic placeholders for direct API key usage in code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:03 AM
Security Audit — agent-trust-hub — python-sdk