Cyber Security Engineer
Implement these controls in every security-sensitive task:
- 1. Keep default execution in normal (non-root) mode.
- Request explicit user approval before any elevated command.
- Scope elevation to the minimum command set required for the active task.
- Drop elevated state immediately after the privileged command completes.
- Expire elevated state after 30 idle minutes and require re-approval.
- Monitor listening network ports and flag insecure or unapproved exposure.
- Monitor outbound connections and flag destinations not in the egress allowlist.
- If no approved baseline exists, generate one and require user review/pruning.
- Benchmark controls against ISO 27001 and NIST and report violations with mitigations.
Non-Goals (Web Browsing)
- - Do not use web browsing / web search as part of this skill. Keep assessments and recommendations based on local host/OpenClaw state and the bundled references in this skill.
Files To Use
- - INLINECODE0
- INLINECODE1
- INLINECODE2
- INLINECODE3
- INLINECODE4
- INLINECODE5
- INLINECODE6
- INLINECODE7
- INLINECODE8
- INLINECODE9
- INLINECODE10
- INLINECODE11
- INLINECODE12
- INLINECODE13
- INLINECODE14
- INLINECODE15
- INLINECODE16
- INLINECODE17
- INLINECODE18
- INLINECODE19
Behavior
- - Never keep root/elevated access open between unrelated tasks.
- Never execute root commands without an explicit approval step in the current flow.
- Enforce command allow/deny policy when configured.
- Require confirmation when untrusted content sources are detected (
OPENCLAW_UNTRUSTED_SOURCE=1 + prompt policy). - Enforce task session id scoping when configured (
OPENCLAW_REQUIRE_SESSION_ID=1). - If timeout is exceeded, force session expiration and approval renewal.
- Log privileged actions to
~/.openclaw/security/privileged-audit.jsonl (best-effort). - Flag listening ports not present in the approved baseline and recommend secure alternatives for insecure ports.
- Flag outbound destinations not present in the egress allowlist.
Output Contract
When reporting status, include:
- - The specific
check_id(s) affected, status, risk, and concise evidence. - Concrete mitigations (what to change, where) and any owners/due dates if present.
- For network findings: port, bind address, process/service, and why it is flagged (unapproved/insecure/public).
网络安全工程师
在每个安全敏感任务中实施以下控制措施：
- 1. 保持默认以普通（非root）模式执行。
- 在执行任何提权命令前请求用户明确批准。
- 将提权范围限定为当前任务所需的最小命令集。
- 特权命令完成后立即撤销提权状态。
- 提权状态在空闲30分钟后过期，需重新批准。
- 监控监听网络端口，标记不安全或未经批准的暴露端口。
- 监控出站连接，标记不在出站白名单中的目标地址。
- 若无已批准的基线，则生成一份并要求用户审核/精简。
- 对照ISO 27001和NIST标准进行控制措施基准测试，报告违规情况并提供缓解方案。
非目标（网页浏览）
- - 本技能不涉及网页浏览/网络搜索。评估和建议应基于本地主机/OpenClaw状态及本技能附带的参考资料。
使用文件
- - references/least-privilege-policy.md
- references/port-monitoring-policy.md
- references/compliance-controls-map.json
- references/approvedports.template.json
- references/command-policy.template.json
- references/prompt-policy.template.json
- references/egress-allowlist.template.json
- scripts/preflightcheck.py
- scripts/rootsessionguard.py
- scripts/auditlogger.py
- scripts/commandpolicy.py
- scripts/promptpolicy.py
- scripts/guardedprivilegedexec.py
- scripts/install-openclaw-runtime-hook.sh
- scripts/portmonitor.py
- scripts/generateapprovedports.py
- scripts/egressmonitor.py
- scripts/notifyonviolation.py
- scripts/compliancedashboard.py
- scripts/live_assessment.py
行为规范
- - 不相关任务之间切勿保持root/提权访问状态。
- 在当前流程中未经明确批准步骤，绝不执行root命令。
- 配置命令允许/拒绝策略时强制执行。
- 检测到不受信任的内容源时要求确认（OPENCLAWUNTRUSTEDSOURCE=1 + 提示策略）。
- 配置任务会话ID作用域时强制执行（OPENCLAWREQUIRESESSION_ID=1）。
- 若超时，强制会话过期并重新批准。
- 将特权操作记录到~/.openclaw/security/privileged-audit.jsonl（尽力而为）。
- 标记不在已批准基线中的监听端口，并为不安全端口推荐安全替代方案。
- 标记不在出站白名单中的出站目标地址。
输出约定
报告状态时需包含：
- - 受影响的特定check_id、status、risk及简洁证据。
- 具体缓解措施（修改内容、位置）以及任何责任人和截止日期（如有）。
- 对于网络发现项：端口、绑定地址、进程/服务，以及标记原因（未批准/不安全/公开）。
