Security audit
Security checks across malware telemetry and agentic risk
The skill mostly matches a brand-marketing workflow, but it includes under-disclosed local credential and messaging-gateway capability that should be reviewed before installation.
Review this skill before installing. It is appropriate only if you are comfortable with brand and competitor data being sent to your configured LLM/search providers, and you should remove or audit gateway_client.py unless you explicitly want Telegram/Feishu messaging through your local OpenClaw gateway token. Do not rely on the bundled benchmark alone as proof of safety.
print(f"[CACHE] TTL expired for {name}, will re-fetch")
# 智能 auth 跳过
def should_skip_auth(action: str, data_access: str, historical_success_rate: float = 0.0) -> bool:
if action in RISK_THRESHOLDS["low"]["actions"] and data_access == "public":
return True
if historical_success_rate > 0.9:66/66 vendors flagged this skill as clean.