examples-auto-run

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution: The skill uses a shell script to invoke pnpm for building the project and running example scripts. This is a standard pattern for automation in development environments and is central to the skill's purpose of streamlining example testing.
  • Dynamic Helper Execution: Internal helpers use node to execute small, inline Javascript blocks for processing configuration. These are used to load skip lists and interactive inputs from local project files, facilitating the automated 'auto-input' mode.
  • Automated Interaction: The runner is configured to automatically approve several interaction types, including Shell tool requests, MCP approvals, and manual intervention prompts (HITL). This is intended to allow the examples to run without user interruption during automated passes.
  • Data Ingestion for Validation: The agent is instructed to read example source code and execution logs to perform behavioral validation. While this involves the agent processing external data, the instructions provide a structured workflow for comparing intended code behavior against actual log output.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 02:25 PM
Security Audit — agent-trust-hub — examples-auto-run