opencode-free-models

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for cost-optimized model routing without any malicious code, obfuscation, or dangerous commands. It focuses on logic for choosing the appropriate model based on task complexity.
  • [SAFE]: It incorporates strong security-conscious guidelines, explicitly instructing the agent to avoid using free or trial models for confidential data, PII, or security-critical tasks like audit verdicts and architecture reviews.
  • [EXTERNAL_DOWNLOADS]: The skill references multiple well-known technology domains and official documentation for AI model providers (such as Google, Hugging Face, and DeepSeek) and the OpenCode platform. These are legitimate references for a model-routing knowledge base.
  • [COMMAND_EXECUTION]: The skill mentions the use of official opencode CLI tools to verify current model availability and pricing. These are standard operational commands for the skill's intended execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:51 AM
Security Audit — agent-trust-hub — opencode-free-models