SKILLEMALL.ai
GitHub ↗ RU Sign in

DD openclaw-push-doctor

openclaw-healthcheck is a self-diagnostic skill that checks and repairs openclaw's communication channels and scheduled tasks. It diagnoses Feishu/lark-cli auth expiry, Telegram bot silence, WeChat bridge disconnects, and cron job failures — then guides the agent through targeted repairs without rebuilding everything from scratch. Trigger words: 飞书断了, 飞书没反应, telegram没反应, 微信断了, 定时任务没推送, cron没跑, 推送失败, 自检一下, 通讯检查, healthcheck, 检查通讯, 定时任务检查, 推送自检, 重连飞书, 重连telegram, 验证码失效, 配对码过期

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Cosmos Fang v1.0.2 MIT-0 11 files body ≈ 530 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerTelegramInfrastructureAI and agentstype 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
52/100
safety, quality, tests
Safety 60%
30
Quality 40%
85
Run on models
none yet
Process rating
D
43/100
Unfinished process
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

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.
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 · 36

  • high Dangerous commands cmd-persistence scripts/fix-crons.js:81
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    crontab /tmp/crontab_backup.txt
  • high Dangerous commands cmd-persistence scripts/fix-crons.js:192
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    crontab /tmp/crontab_backup.txt
Medium and low: 34
  • low Exfiltration exfil-webhook-url scripts/check-all.js:49
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe" | \\
    placeholder
  • low Exfiltration net-credential-use scripts/check-all.js:49
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe" | \\
    vendor-hostquoted
  • low Exfiltration exfil-webhook-url scripts/check-all.js:54
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getUpdates?limit=1" | \\
    placeholder
  • low Exfiltration net-credential-use scripts/check-all.js:54
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getUpdates?limit=1" | \\
    vendor-hostquoted
  • low Dangerous commands cmd-cron-mention scripts/check-all.js:84
    Mentions editing / listing crontab (string literal in code, not executed)
    openclaw cron list 2>/dev/null || crontab -l 2>/dev/null | grep -i openclaw || echo "NO_CRON_FOUND"
    code literal
  • low Dangerous commands cmd-cron-mention scripts/check-all.js:87
    Mentions editing / listing crontab (string literal in code, not executed)
    crontab -l 2>/dev/null | sort | uniq -d | head -20
    code literal
  • low Exfiltration exfil-webhook-url scripts/check-all.js:153
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe" | \\
    placeholder
  • low Exfiltration net-credential-use scripts/check-all.js:153
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe" | \\
    vendor-hostquoted
  • low Exfiltration exfil-webhook-url scripts/check-all.js:158
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getUpdates?limit=1" | \\
    placeholder
  • low Exfiltration net-credential-use scripts/check-all.js:158
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getUpdates?limit=1" | \\
    vendor-hostquoted
  • low Dangerous commands cmd-cron-mention scripts/check-all.js:188
    Mentions editing / listing crontab (string literal in code, not executed)
    openclaw cron list 2>/dev/null || crontab -l 2>/dev/null | grep -i openclaw || echo "NO_CRON_FOUND"
    code literal
  • low Dangerous commands cmd-cron-mention scripts/check-all.js:191
    Mentions editing / listing crontab (string literal in code, not executed)
    crontab -l 2>/dev/null | sort | uniq -d | head -20
    code literal
  • low Dangerous commands cmd-cron-mention scripts/check-crons.js:22
    Mentions editing / listing crontab (string literal in code, not executed)
    crontab -l 2>/dev/null | grep -i "openclaw\\|morning-push\\|daily-push" | cat || \\
    code literal
  • low Dangerous commands cmd-cron-mention scripts/check-crons.js:26
    Mentions editing / listing crontab (string literal in code, not executed)
    crontab -l 2>/dev/null | sort | uniq -d
    code literal
  • low Dangerous commands cmd-cron-mention scripts/check-crons.js:48
    Mentions editing / listing crontab (string literal in code, not executed)
    crontab -l 2>/dev/null | grep -i "openclaw\\|morning-push\\|daily-push" | cat || \\
    code literal
  • low Dangerous commands cmd-cron-mention scripts/check-crons.js:52
    Mentions editing / listing crontab (string literal in code, not executed)
    crontab -l 2>/dev/null | sort | uniq -d
    code literal
  • low Exfiltration exfil-webhook-url scripts/check-telegram.js:45
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe"
    placeholder
  • low Exfiltration exfil-webhook-url scripts/check-telegram.js:58
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getUpdates?limit=1&timeout=5"
    placeholder
  • low Exfiltration exfil-webhook-url scripts/check-telegram.js:62
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getWebhookInfo"
    placeholder
  • low Exfiltration exfil-webhook-url scripts/check-telegram.js:74
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/deleteWebhook"
    placeholder
  • low Exfiltration net-credential-use scripts/check-telegram.js:74
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    curl -s "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/deleteWebhook"
    vendor-hostquoted
  • low Exfiltration exfil-webhook-url scripts/check-telegram.js:98
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe"
    placeholder
  • low Exfiltration net-credential-use scripts/check-telegram.js:98
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe"
    vendor-host
  • low Exfiltration net-credential-use scripts/check-telegram.js:165
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    curl -s "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/deleteWebhook"
    vendor-hostquoted
  • low Exfiltration net-credential-use scripts/check-telegram.js:189
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -s --max-time 10 "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getMe"
    vendor-host
  • low Dangerous commands cmd-cron-mention scripts/fix-crons.js:38
    Mentions editing / listing crontab (string literal in code, not executed)
    crontab -l 2>/dev/null | grep -i "openclaw\\|morning-push\\|daily-push\\|skill" | cat
    code literal
  • low Dangerous commands cmd-cron-mention scripts/fix-crons.js:59
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | sort | uniq -d
  • low Dangerous commands cmd-cron-mention scripts/fix-crons.js:62
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -i "openclaw\\|morning-push" | sort
  • low Dangerous commands cmd-cron-mention scripts/fix-crons.js:69
    Mentions editing / listing crontab
    crontab -l > /tmp/crontab_backup.txt
  • low Dangerous commands cmd-cron-mention scripts/fix-crons.js:83
    Mentions editing / listing crontab
    crontab -l | grep openclaw
  • low Exfiltration exfil-webhook-url scripts/fix-crons.js:118
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \\
    placeholder
  • low Exfiltration net-credential-use scripts/fix-crons.js:118
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \\
    vendor-host
  • low Exfiltration exfil-webhook-url scripts/fix-crons.js:229
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \\
    placeholder
  • low Exfiltration net-credential-use scripts/fix-crons.js:229
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \\
    vendor-host

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "keywords"
  • note frontmatter-key unknown frontmatter key "requirements"

Process rating: all ten parameters 43/100

  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (node) that frontmatter does not declare
  • 100Steps. 5 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 530 tokens

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 479: enough signal without eating the budget
  • +4Structure: 6 headings
  • +3Step-by-step instructions: 5 items
  • +4Has examples (2 code blocks)
  • +3All 7 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: clean
The skill is a disclosed OpenClaw diagnostic and repair helper that prints guidance for checking push channels and cron jobs, with some sensitive repair steps users should run only deliberately.
LLM: benign (high) · VirusTotal: · 29 May 2026