SKILLEMALL.ai
GitHub ↗ RU Sign in

DC deadclaw

Emergency kill switch for OpenClaw agents. Instantly halts all running agents, pauses scheduled jobs, kills active sessions, and logs everything — triggered by a single message, a WebChat button, or a phone home screen shortcut. Includes a background watchdog that auto-kills agents on runaway loops, excessive token spend, unauthorized network calls, or out-of-bounds file writes. Use this skill whenever the user mentions: emergency stop, kill switch, stop agents, halt agents, panic button, deadclaw, agent safety, runaway agent, kill all, stop everything, or any urgent need to shut down OpenClaw processes immediately.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Zen Fox v1.0.1 MIT-0 27 files · 4 scripts body ≈ 1 619 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorAI 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%
27
Quality 40%
90
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 14

  • high Dangerous commands cmd-persistence scripts/kill.sh:319
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    for plist in ~/Library/LaunchAgents/com.openclaw.*; do
  • high Dangerous commands cmd-persistence scripts/restore.sh:233
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    for plist in ~/Library/LaunchAgents/com.openclaw.*; do
  • high Dangerous commands cmd-persistence scripts/restore.sh:235
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$plist" 2>/dev/null || true
Medium and low: 11
  • medium Dangerous commands cmd-persistence scripts/kill.sh:308
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v -i "openclaw\|claw-agent\|clawdbot\|moltbot" | crontab - 2>/dev/null || true
    detector
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: bash
    allowed-tools: bash messaging webchat
  • low Exfiltration exfil-webhook-url docs/android-widget-guide.md:44
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - **URL**: `https://api.telegram.org/botYOUR_BOT_TOKEN_HERE/sendMessage`
    placeholder
  • low Exfiltration exfil-webhook-url docs/android-widget-guide.md:99
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    4. **URL**: `https://api.telegram.org/botYOUR_BOT_TOKEN_HERE/sendMessage`
    placeholder
  • low Secrets in code secret-telegram-bot docs/android-widget-guide.md:101
    Telegram bot token (placeholder value)
    Replace `YOUR_BOT_TOKEN_HERE` with your actual Telegram bot token. You got this from BotFather when you created your bot. It looks like `7123…AHx…`.
    placeholder
  • low Secrets in code secret-telegram-bot docs/android-widget-guide.md:166
    Telegram bot token (placeholder value)
    5. Copy the token (looks like `7123…AHx…`)
    placeholder
  • low Exfiltration exfil-webhook-url docs/iphone-shortcut-guide.md:54
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    https://api.telegram.org/botYOUR_BOT_TOKEN_HERE/sendMessage
    placeholder
  • low Secrets in code secret-telegram-bot docs/iphone-shortcut-guide.md:56
    Telegram bot token (placeholder value)
    **REPLACE** `YOUR_BOT_TOKEN_HERE` with your actual Telegram bot token. It looks something like `7123…AHx…`. You got this when you created your bot with BotFather.
    placeholder
  • low Dangerous commands cmd-cron-mention scripts/kill.sh:294
    Mentions editing / listing crontab
    if crontab -l &>/dev/null; then
  • low Dangerous commands cmd-cron-mention scripts/kill.sh:295
    Mentions editing / listing crontab
    crontab -l > "$backup_file" 2>/dev/null || true
  • low Dangerous commands cmd-cron-mention scripts/kill.sh:308
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v -i "openclaw\|claw-agent\|clawdbot\|moltbot" | crontab - 2>/dev/null || true

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "trigger_keywords"

Process rating: all ten parameters 64/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 8 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 27 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1619 tokens
  • 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

  • +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 623: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 27 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (2 of 6)
  • +3All 4 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

External checks

ClawHub: suspicious
DeadClaw appears to be a real emergency stop tool, but it gives remote, easily triggered shutdown and restore authority without enough scoping or safeguards.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026