CD openclaw-soul
OpenClaw 自我进化框架一键部署。安装宪法(AGENTS.md)、可进化灵魂(SOUL.md)、心跳系统、六层记忆架构、目标管理、思维方法论（HDD/SDD）、安全审查（skill-vetter），并通过场景化对话引导用户定义 Agent 性格。用户可选安装 EvoClaw（审批制进化）、Self-Improving Agent（自主学习）等依赖 Skill。触发场景：(1) 用户说"灵魂框架"、"部署灵魂"、"部署灵魂系统" (2) 用户说"BOOTSTRAP"、"首次对话"、"第一次对话" (3) 用户说"安装进化框架"、"部署进化框架" (4) 用户提到"openclaw-soul"。注意：这是 OpenClaw 部署的第一步，完成后会引导使用 openclaw-setup 配置技术参数。
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Dangerous commands medium severity
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
If you install
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
For the author
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 10
✓ No critical or high findings
Medium and low: 10
-
medium Dangerous commands
cmd-persistenceSKILL.md:649Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "openclaw heartbeat.*--agent last$"; echo "7 * * * * openclaw heartbeat --agent last 2>&1 | logger -t openclaw-heartbeat") | crontab -
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:657Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "merge-daily-transcript"; echo "17 2 * * * cd $WORKSPACE && node scripts/merge-daily-transcript.js 2>&1 | logger -t openclaw-memory") | crontab -
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:663Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "auto-commit.sh"; echo "23 */6 * * * cd $WORKSPACE && bash scripts/auto-commit.sh 2>&1 | logger -t openclaw-git") | crontab -
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:678Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "openclaw heartbeat.*daily-report"; echo "0 20 * * * openclaw heartbeat --agent last --prompt '读取 GOALS.md，汇报今天的目标完成情况，提醒明天的重要任务。如果有被遗忘的任务或即将到期的 deadline，主动提醒用户。' 2>&
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:684Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "openclaw heartbeat.*weekly-reflection"; echo "0 21 * * 0 openclaw heartbeat --agent last --prompt '回顾本周的对话记录（读取 memory/transcripts/ 最近7天的文件），生成深度反思：1. 本周完成了什么 2. 遇到了
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:649Mentions editing / listing crontab (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "openclaw heartbeat.*--agent last$"; echo "7 * * * * openclaw heartbeat --agent last 2>&1 | logger -t openclaw-heartbeat") | crontab -
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:657Mentions editing / listing crontab (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "merge-daily-transcript"; echo "17 2 * * * cd $WORKSPACE && node scripts/merge-daily-transcript.js 2>&1 | logger -t openclaw-memory") | crontab -
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:663Mentions editing / listing crontab (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "auto-commit.sh"; echo "23 */6 * * * cd $WORKSPACE && bash scripts/auto-commit.sh 2>&1 | logger -t openclaw-git") | crontab -
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:678Mentions editing / listing crontab (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "openclaw heartbeat.*daily-report"; echo "0 20 * * * openclaw heartbeat --agent last --prompt '读取 GOALS.md，汇报今天的目标完成情况，提醒明天的重要任务。如果有被遗忘的任务或即将到期的 deadline，主动提醒用户。' 2>&
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:684Mentions editing / listing crontab (documentation of a security skill)(crontab -l 2>/dev/null | grep -v "openclaw heartbeat.*weekly-reflection"; echo "0 21 * * 0 openclaw heartbeat --agent last --prompt '回顾本周的对话记录（读取 memory/transcripts/ 最近7天的文件），生成深度反思：1. 本周完成了什么 2. 遇到了
security skill
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7794 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, git, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 7794 tokens
- 100Steps. 92 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 355: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 92 items
- +4Has examples (46 code blocks)
- +4Reference files are cited in the instructions (12 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.
External checks
ClawHub: suspicious
This skill is a disclosed self-evolving OpenClaw setup, but it grants broad persistent authority over memory, configuration, credentials, cron jobs, and repository state that users should review carefully before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026