SKILLEMALL.ai
GitHub ↗ RU Sign in

DC config-modification-safety

OpenClaw 配置安全守护。防止 AI 改坏配置文件的双层守护架构，支持 macOS 和 Windows。 触发场景：AI 修改配置文件后系统崩溃、JSON 语法错误导致 Gateway 无法启动、想给 OpenClaw 配置安全网。 核心功能： - 第一层（铜墙）：配置文件变更时自动校验 JSON，语法错误 1 秒内回滚 - 第二层（铁壁）：每 5 分钟检查 Gateway 健康状态，崩溃自动恢复 - 应急回滚：一行命令恢复到最后一次正常配置 安装后用户获得：铜墙铁壁级别的配置保护，AI 改配置再也不怕搞崩系统了。

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: alexduming v1.0.0 MIT-0 7 files · 2 scripts body ≈ 571 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
53/100
safety, quality, tests
Safety 60%
42
Quality 40%
69
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 7

  • high Dangerous commands cmd-persistence scripts/install.sh:27
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST_DST" 2>/dev/null || echo "  (可能已加载，跳过)"
  • high Dangerous commands cmd-persistence scripts/install.sh:34
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "config-safety/health-check"; echo "$CRON_LINE") | crontab -
  • high Dangerous commands cmd-persistence SKILL.md:61
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.openclaw.config-guard.plist
Medium and low: 4
  • low Dangerous commands cmd-persistence scripts/install.sh:23
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    PLIST_DST="$HOME/Library/LaunchAgents/com.openclaw.config-guard.plist"
    detectorcode literal
  • low Dangerous commands cmd-cron-mention scripts/install.sh:34
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "config-safety/health-check"; echo "$CRON_LINE") | crontab -
  • low Dangerous commands cmd-persistence scripts/install.sh:51
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    echo "  卸载：launchctl unload $HOME/Library/LaunchAgents/com.openclaw.config-guard.plist && crontab -r"
    detectorcode literal
  • low Dangerous commands cmd-cron-mention SKILL.md:62
    Mentions editing / listing crontab
    crontab -e  # 删除 config-safety 那行

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 11 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 571 tokens
  • 100Running it twice. No mutating operations

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 263: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
The skill is a plausible OpenClaw config safety tool, but it installs persistent automation that can overwrite configs and restart services, with incomplete install artifacts and unsafe removal guidance.
LLM: suspicious (high) · VirusTotal: · 29 May 2026