Smart Agent Template

Smart Agent 工作流模板：三重判断机制 + 自动更新 + Context 优化。包含完整的任务执行规范、WBS 拆分、流程豁免阈值、记忆管理等最佳实践。

Before installing or running this skill: 1) Treat the repo as code that will run on your system — audit scripts/auto_update.sh and any start scripts. 2) Disable automatic updates (set config/auto_update.yaml enabled: false and do not run auto_update.sh) until you trust the source. 3) Inspect any code that will be run on startup (bot entrypoints, auto-update, health/metrics scripts) and verify they don't call external URLs you don't expect. 4) Be cautious about enabling integrations — only set FEISHU/TELEGRAM/CLAUDE/OPENAI/OLLAMA credentials if you reviewed the integration code; keep secrets out of shared/mounted workspaces. 5) If you plan to let other agents 'read and obey' AGENTS.md or inject it into system prompts, be aware this is effectively a system-prompt override; only do so with fully audited content. 6) Prefer running in an isolated environment (container or VM) and limit network access until you've audited the update mechanism and webhook handlers. 7) If you need higher assurance, ask the publisher for a source URL / signed release; absence of a homepage and unknown owner ID reduces trust.

Type: OpenClaw Skill Name: smart-agent-template Version: 1.1.0 The skill bundle is classified as suspicious due to several high-risk security practices and intentional security bypasses. Most notably, 'integrations/feishu/start_longconn.sh' and 'integrations/feishu/start_bot.py' explicitly disable SSL certificate verification, with the former even using a Python script to patch the 'lark-oapi' library code on the local disk to force an unverified SSL context. Additionally, 'scripts/auto_update.sh' implements an auto-update mechanism that performs a 'git pull' from a remote repository (github.com/whhaijun/agent-workflow.git), which introduces a significant supply chain risk and potential for remote code execution. While these appear to be misguided 'convenience' features for developers, they create critical vulnerabilities like Man-in-the-Middle (MITM) and unauthorized code execution.