Security audit
Security checks across malware telemetry and agentic risk
The skill is a coherent AI API router, but it handles API keys, sends prompts to multiple outside providers, writes persistent local cache/state, and uses broad install/setup behavior that users should review first.
Install only if you are comfortable with this skill using your AI provider API keys, sending prompts/system text to selected third-party providers, and storing response cache/state under your home directory. Avoid passing API keys on the command line on shared systems; use non-sensitive prompts for probes; run with --no-cache for sensitive work; and review get-ai-router.sh before using the one-file bootstrap.
if use_cache:
try:
json.dump({'text': text, 'provider': prov, 'model': model},
open(cache_path(prompt, system, task,
max_tokens, quality), 'w'))
except Exception: pass
return text, prov, model, Falsetxt, code, t = curl(url, ['Content-Type: application/json', f'X-goog-api-key: {k}'], body)
else:
cfg = {
'mistral': ('https://api.mistral.ai/v1/chat/completions', creds('mistral')['api_key'], []),
'openrouter': ('https://openrouter.ai/api/v1/chat/completions', creds('openrouter')['api_key'],
['HTTP-Referer: https://arena.ai','X-Title: ArenaAgentMode']),
'kilo': ('https://api.kilo.ai/api/gateway/chat/completions', creds('kilo')['api_key'],'mistral': ('https://api.mistral.ai/v1/chat/completions', creds('mistral')['api_key'], []),
'openrouter': ('https://openrouter.ai/api/v1/chat/completions', creds('openrouter')['api_key'],
['HTTP-Referer: https://arena.ai','X-Title: ArenaAgentMode']),
'kilo': ('https://api.kilo.ai/api/gateway/chat/completions', creds('kilo')['api_key'],
['X-KILOCODE-FEATURE: arena-agent']),
'cerebras': ('https://api.cerebras.ai/v1/chat/completions', creds('cerebras')['api_key'], []),
}[prov]['HTTP-Referer: https://arena.ai','X-Title: ArenaAgentMode']),
'kilo': ('https://api.kilo.ai/api/gateway/chat/completions', creds('kilo')['api_key'],
['X-KILOCODE-FEATURE: arena-agent']),
'cerebras': ('https://api.cerebras.ai/v1/chat/completions', creds('cerebras')['api_key'], []),
}[prov]
url, key, extra = cfg
body = json.dumps({'model':model,'messages':[{'role':'user','content':PROMPT}],'max_tokens':2000})body=json.dumps({'contents':[{'parts':[{'text':q}]}],'generationConfig':{'maxOutputTokens':2500}})
else:
url,key,extra={
'mistral':('https://api.mistral.ai/v1/chat/completions',creds('mistral')['api_key'],[]),
'openrouter':('https://openrouter.ai/api/v1/chat/completions',creds('openrouter')['api_key'],
['HTTP-Referer: https://arena.ai','X-Title: ArenaAgentMode']),
'kilo':('https://api.kilo.ai/api/gateway/chat/completions',creds('kilo')['api_key'],'mistral':('https://api.mistral.ai/v1/chat/completions',creds('mistral')['api_key'],[]),
'openrouter':('https://openrouter.ai/api/v1/chat/completions',creds('openrouter')['api_key'],
['HTTP-Referer: https://arena.ai','X-Title: ArenaAgentMode']),
'kilo':('https://api.kilo.ai/api/gateway/chat/completions',creds('kilo')['api_key'],
['X-KILOCODE-FEATURE: arena-agent']),
}[prov]
h=['Content-Type: application/json',f'Authorization: Bearer {key}']+extra# request fail with "no credentials" — even when routing elsewhere.
# Build only the provider we are actually calling.
endpoints = {
'mistral': ('https://api.mistral.ai/v1/chat/completions', []),
'openrouter': ('https://openrouter.ai/api/v1/chat/completions',
['HTTP-Referer: https://arena.ai', 'X-Title: ArenaAgentMode']),
'kilo': ('https://api.kilo.ai/api/gateway/chat/completions','mistral': ('https://api.mistral.ai/v1/chat/completions', []),
'openrouter': ('https://openrouter.ai/api/v1/chat/completions',
['HTTP-Referer: https://arena.ai', 'X-Title: ArenaAgentMode']),
'kilo': ('https://api.kilo.ai/api/gateway/chat/completions',
['X-KILOCODE-FEATURE: arena-agent']),
'cerebras': ('https://api.cerebras.ai/v1/chat/completions', []),
}name: free-tier-ai-router
description: Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras. Probes every model on every key, measures real quality and real published rate limits, then routes each request to the cheapest model that can do the job — spending abundant capacity first and reserving scarce daily quota for when it is actually needed. Persists cooldowns to disk so a 429 discovered in one process is respected by the next. Use when an agent must make many LLM calls on free keys without hitting rate limits, when "all models failed", or when deciding which of several provider keys to use for a task.
version: 2.1.0
metadata: {"openclaw":{"emoji":"🎛️","requires":{"bins":["curl","python3"]},"configPaths":["~/.config/gemini/credentials.json","~/.config/mistral/credentials.json","~/.config/openrouter/credentials.json","~/.config/kilo/credentials.json","~/.cache/ai_router/state.json"],"network":{"outbound":["generativelanguage.googleapis.com","api.mistral.ai","openrouter.ai","api.kilo.ai","api.cerebras.ai"]}}}
---
# 🎛️ free-tier-ai-routername: free-tier-ai-router
description: Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras. Probes every model on every key, measures real quality and real published rate limits, then routes each request to the cheapest model that can do the job — spending abundant capacity first and reserving scarce daily quota for when it is actually needed. Persists cooldowns to disk so a 429 discovered in one process is respected by the next. Use when an agent must make many LLM calls on free keys without hitting rate limits, when "all models failed", or when deciding which of several provider keys to use for a task.
version: 2.1.0
metadata: {"openclaw":{"emoji":"🎛️","requires":{"bins":["curl","python3"]},"configPaths":["~/.config/gemini/credentials.json","~/.config/mistral/credentials.json","~/.config/openrouter/credentials.json","~/.config/kilo/credentials.json","~/.cache/ai_router/state.json"],"network":{"outbound":["generativelanguage.googleapis.com","api.mistral.ai","openrouter.ai","api.kilo.ai","api.cerebras.ai"]}}}
---
# 🎛️ free-tier-ai-routerVirusTotal findings are pending for this skill version.
No suspicious patterns detected.