Skills
skills/infsh-skills/skills/javascript-sdk/Gen Agent Trust Hub

javascript-sdk

Warn

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Documentation examples in references/tool-builder.md and references/agent-patterns.md demonstrate the use of the JavaScript eval() function to execute code derived from AI agent input (specifically for a calculator tool implementation). This practice is highly dangerous as it allows for arbitrary code execution if the agent is manipulated via prompt injection to provide malicious commands instead of mathematical expressions.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @inferencesh/sdk package from the npm registry and the belt-sh/cli tool. These resources are recognized as official components of the vendor's infrastructure or related ecosystem tools.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 22, 2026, 11:51 AM
Security Audit — agent-trust-hub — javascript-sdk