SKILLEMALL.ai
GitHub ↗ RU Sign in

CC openclaw-safety-guard

OpenClaw 安全卫士（发布 slug：openclaw-safety-guard，内部代号：openclaw-watchdog）：默认工作日 10:00 自动扫描 7 个维度（安全、记忆、心跳、定时任务、共享文件、通讯、代码规范），生成健康评分和可视化 Dashboard，通过飞书私信发送报告；没有 Cursor 也可直接看 dashboard 和下载 JSON。用户说「体检」「生成健康大盘」「跑安全检查」时手动触发。

ClawHub Agent Skills author: jasonzhangshuo v0.1.1 28 files body ≈ 652 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceData and analyticsInfrastructuretype 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
C
67/100
safety, quality, tests
Safety 60%
66
Quality 40%
69
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation 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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

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

  1. 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 · 14

✓ No critical or high findings

Medium and low: 14
  • medium Obfuscation obf-base64-blob frontend/src/imports/Body.tsx:2
    Long base64-looking blob
    import imgA…AU1
  • medium Obfuscation obf-base64-blob frontend/src/imports/Body.tsx:1743
    Long base64-looking blob
    function Ab6A…U1W
  • medium Obfuscation obf-base64-blob frontend/src/imports/Body.tsx:1747
    Long base64-looking blob
    <img alt="" className="absolute left-0 max-w-none size-full top-0" src={imgA…vkn
  • medium Obfuscation obf-base64-blob frontend/src/imports/Body.tsx:1757
    Long base64-looking blob
    <Ab6A…J3Q
  • medium Dangerous commands cmd-persistence scripts/fix_green.py:20
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_PATH = os.path.expanduser("~/Library/LaunchAgents/ai.openclaw.gateway.plist")
    code literal
  • low Dangerous commands cmd-persistence config.example.json:10
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed; security demo / example; test fixture / example file)
    "target": "~/Library/LaunchAgents/ai.openclaw.gateway.plist"
    detectorcode literaldemofixture
  • low Secrets in code secret-high-entropy-token frontend/package-lock.json:144
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…1Ku+MY3k…vfJ+Q61m0xktWwt+1HSY…RJg==",
    detector
  • low Secrets in code secret-high-entropy-token frontend/package-lock.json:364
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…SzS+cfgl…B0A==",
    detector
  • low Secrets in code secret-high-entropy-token frontend/package-lock.json:409
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Om3+5ZRS…Lw6+EGyk…kl3+UP9+sdz7…Y3g==",
    detector
  • low Secrets in code secret-high-entropy-token frontend/package-lock.json:415
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…HUa+lAWK…Kd7+Khib…5lw==",
    detector
  • low Secrets in code secret-high-entropy-token frontend/package-lock.json:523
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…ToE+vYgD…UJ8+N1Am3Mz4+xOBy…f4D+CpkA==",
    detector
  • low Obfuscation obf-base64-blob frontend/src/imports/Body.tsx:1745
    Long base64-looking blob (quoted — discussed, not commanded)
    <div className="flex-[1_0_0] min-h-px min-w-px relative rounded-[9999px] w-full" data-name="AB6A…hTD
    quoted
  • low Dangerous commands cmd-persistence scripts/setup.py:105
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed; security demo / example)
    {"id": "plist_permissions", "enabled": True, "target": "~/Library/LaunchAgents/ai.openclaw.gateway.plist"},
    detectorcode literaldemo

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 28. 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 53/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 8 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 652 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
  • -32 of 15 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 214: enough signal without eating the budget
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 8 items
  • +4Has examples (4 code blocks)

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

External checks

ClawHub: suspicious
This appears to be a real OpenClaw health monitor, but it creates recurring execution, sends local security summaries to Feishu, and applies a local permission change without separate approval steps.
LLM: suspicious (high) · VirusTotal: · 29 May 2026