styx-gateway — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited styx-gateway (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You have access to a running Styx gateway that proxies and manages LLM API traffic across multiple providers.
Styx is a unified gateway that sits between your application and AI providers (OpenAI, Anthropic, Google, Mistral, etc.). It provides:
http://localhost:8080/v1/chat/completions using OpenAI-compatible format/mcplist_providers — List all configured AI providers and their statuslist_models — List available models across all providersget_usage — Get usage statistics for a time rangeget_health — Check gateway health and provider connectivitycreate_api_key — Generate a new API key with optional rate limitsrevoke_api_key — Revoke an existing API keylist_api_keys — List all API keys and their statusget_cache_stats — View cache hit rates and savingsroute_request — Send a chat completion through the gatewayUse get_health to verify Styx is running and all providers are reachable.
Use get_usage with a date range to see token consumption and costs by provider and model.
Use create_api_key with rate limit parameters to generate keys for specific applications or team members.
If Styx is not yet running:
git clone https://github.com/styx-hq/styx.git
cd styx && ./setup.sh && docker compose up -dGateway: http://localhost:8080 | Dashboard: http://localhost:3000
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.