choose-approach

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides purely instructional content. It acts as a heuristic for determining whether to use classical NLP, local LLMs, or cloud-based LLMs based on corpus size and task complexity.
  • [SAFE]: No code, scripts, or automated tool invocations are present. The skill instructs the agent to present information and cost estimates to the user before proceeding.
  • [SAFE]: References to external services like OpenRouter, Anthropic, and OpenAI are for pricing estimation and model selection purposes, following best practices for cost management and task optimization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 03:12 AM
Security Audit — agent-trust-hub — choose-approach