venice — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited venice (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.
Wanneer gebruiken: Als je gebruiker vraagt om iets te zoeken/onderzoeken via Venice AI, of wil dat Wolfie iets analyseert met Venice.
Belangrijk: Deze skill draait ALTIJD in een geïsoleerde subagent. De main session blijft beschikbaar. Spreek nooit Venice direct aan vanuit de main session.
Check voor de API key in environment variabelen:
VENICE_API_KEY (format: vapi_xxx)VENICE_API_KEY_SECRET (indien relevant)Endpoint: https://api.venice.ai/api/v1/chat/completions
Headers:
Authorization: Bearer $VENICE_API_KEY
Content-Type: application/jsonBody:
{
"model": "venice-uncensored",
"messages": [
{"role": "system", "content": "Je bent een behulpzame onderzoeksassistent."},
{"role": "user", "content": "<vraag van gebruiker>"}
],
"max_tokens": 2048,
"temperature": 0.7
}Schrijf het Venice antwoord naar: ~/.openclaw/workspace/tmp/venice_result_YYYYMMDD_HHMMSS.txt
~/.openclaw/workspace/config/venice.key~/.venice.key~/.openclaw/workspace/notes/venice_api_key.txtfor attempt in range(3):
try:
response = requests.post(endpoint, headers=headers, json=payload, timeout=60)
if response.status_code == 200:
result = response.json()
answer = result["choices"][0]["message"]["content"]
break
except Exception as e:
if attempt == 2:
print(f"FAILED: {e}")
time.sleep(5)Na het schrijven van het antwoord:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.