Security audit
Security checks across malware telemetry and agentic risk
This memory skill mostly matches its purpose, but it under-discloses sending remembered conversation text to an external embedding API using locally discovered credentials.
Install only if you trust the publisher and are comfortable with conversation memory being saved locally and sent to the configured BigModel/Zhipu embedding service. Use a dedicated low-scope API key, avoid storing secrets or regulated data, review the memory directory regularly, and run cleanup in dry-run mode before deleting records.
}
try:
response = requests.post(url, headers=headers, json=data, timeout=30)
response.raise_for_status()
result = response.json()
if 'data' in result and len(result['data']) > 0:log_entry += "\n".join([f" • {m.get('content', '')[:100]}..." for m in short_memories[-5:]])
log_entry += "\n"
with open(log_file, 'a', encoding='utf-8') as f:
f.write(log_entry)
print(f" ✓ 已生成日志: {log_file}")new_entry = f"\n\n## {date_str} (手动提取)\n\n"
new_entry += "\n".join(decisions_found)
with open(l1_decisions_file, 'a', encoding='utf-8') as f:
f.write(new_entry)
print(f"✓ 已更新 key-decisions.md (新增 {len(decisions_found)} 条)")new_entry = f"\n\n## {date_str} (自动保存)\n\n"
new_entry += "\n".join(decisions_found)
with open(l1_decisions_file, 'a', encoding='utf-8') as f:
f.write(new_entry)
print(f" ✓ 已更新 key-decisions.md (新增 {len(decisions_found)} 条)")64/64 vendors flagged this skill as clean.