Skills/ClawHub/deadclaw

deadclaw@1.0.1

CAUTION· static only

Publisher claims: "Emergency kill switch for OpenClaw agents. Instantly halts all running agents, pauses scheduled jobs, kills active sessions, and logs everything — triggered..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher kintupercy · publishing for 249 daysInstalls 1,611Last detonated 34 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Process kill commanddeadclaw/SKILL.md:4 · Process kill command — agent can terminate processesEmergency kill switch for OpenClaw agents. Instantly halts all running agents,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/kill.sh:19 · Process kill command — agent can terminate processes# ./kill.sh --dry-run # Log what would happen, don't kill anythingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/restore.sh:4 · Process kill command — agent can terminate processes# Post-kill recovery script. Restores the backed-up crontab and optionallyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/watchdog.sh:4 · Process kill command — agent can terminate processes# Background monitor daemon that auto-triggers the kill script when it detectsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/restore.sh:20 · Process kill command — agent can terminate processes# kill event, you want to be sure before bringing things back online.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/SKILL.md:10 · Process kill command — agent can terminate processesbutton, deadclaw, agent safety, runaway agent, kill all, stop everything, or anyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/status.sh:228 · Process kill command — agent can terminate processeswarnings+=("Token spend is at ${token_total} — approaching ${max_tokens} kill threshold")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/kill.sh:4 · Process kill command — agent can terminate processes# Core emergency kill script for OpenClaw agents.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:9 · Process kill command — agent can terminate processesthe user mentions: emergency stop, kill switch, stop agents, halt agents, panicFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/status.sh:223 · Process kill command — agent can terminate processeswarnings+=("Agent ${agent_names[$i]} (PID ${agent_pids[$i]}) has been running ${agent_uptimes[$i]} — approaching ${max_runtime}min kill threshold")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/kill.sh:127 · Process kill command — agent can terminate processes# Graceful: kill sessions inside the container firstFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/kill.sh:18 · Process kill command — agent can terminate processes# ./kill.sh # Execute the killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/kill.sh:240 · Process kill command — agent can terminate processeslog_event "DRY-RUN: Would kill PID $pid ($(ps -p "$pid" -o comm= 2>/dev/null || echo 'unknown'))"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/SKILL.md:9 · Process kill command — agent can terminate processesthe user mentions: emergency stop, kill switch, stop agents, halt agents, panicFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentdeadclaw/docs/iphone-shortcut-guide.md:87 · HTML comment carrying imperative instructions to the agentSCREENSHOT_PLACEHOLDER: test-run-result.pngFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commanddeadclaw/SKILL.md:34 · Process kill command — agent can terminate processesDeadClaw is a single-purpose emergency kill switch. When triggered, it immediatelyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:34 · Process kill command — agent can terminate processesDeadClaw is a single-purpose emergency kill switch. When triggered, it immediatelyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/SKILL.md:15 · Process kill command — agent can terminate processes- killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:10 · Process kill command — agent can terminate processesbutton, deadclaw, agent safety, runaway agent, kill all, stop everything, or anyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:4 · Process kill command — agent can terminate processesEmergency kill switch for OpenClaw agents. Instantly halts all running agents,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentdocs/iphone-shortcut-guide.md:87 · HTML comment carrying imperative instructions to the agentSCREENSHOT_PLACEHOLDER: test-run-result.pngFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commanddeadclaw/scripts/status.sh:160 · Process kill command — agent can terminate processesif kill -0 "$wpid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:15 · Process kill command — agent can terminate processes- killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/status.sh:208 · Process kill command — agent can terminate processesif kill -0 "$watchdog_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/kill.sh:136 · Process kill command — agent can terminate processes# Graceful: kill sessions inside the container firstFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/kill.sh:19 · Process kill command — agent can terminate processes# ./kill.sh --dry-run # Log what would happen, don't kill anythingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/kill.sh:4 · Process kill command — agent can terminate processes# Core emergency kill script for OpenClaw agents.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/kill.sh:18 · Process kill command — agent can terminate processes# ./kill.sh # Execute the killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/watchdog.sh:402 · Process kill command — agent can terminate processesif kill -0 "$existing_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/restore.sh:4 · Process kill command — agent can terminate processes# Post-kill recovery script. Restores the backed-up crontab and optionallyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/watchdog.sh:417 · Process kill command — agent can terminate processes# Clean up PID file on exit (TERM from kill command, INT from Ctrl-C)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/watchdog.sh:17 · Process kill command — agent can terminate processes# ./watchdog.sh start --dry-run # Monitor and log but don't auto-killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/kill.sh:254 · Process kill command — agent can terminate processeslog_event "DRY-RUN: Would kill PID $pid ($(ps -p "$pid" -o comm= 2>/dev/null || echo 'unknown'))"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddeadclaw/scripts/watchdog.sh:126 · Process kill command — agent can terminate processes# Trigger the kill script with a reasonFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/status.sh:208 · Process kill command — agent can terminate processesif kill -0 "$watchdog_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/restore.sh:293 · Process kill command — agent can terminate processes# Send confirmation — don't auto-start the watchdog. After a kill event,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:423 · Process kill command — agent can terminate processes# Clean up PID file on exit (TERM from kill command, INT from Ctrl-C)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/status.sh:223 · Process kill command — agent can terminate processeswarnings+=("Agent ${agent_names[$i]} (PID ${agent_pids[$i]}) has been running ${agent_uptimes[$i]} — approaching ${max_runtime}min kill threshold")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:408 · Process kill command — agent can terminate processesif kill -0 "$existing_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
HTML comment carrying imperative instructions to the agentdeadclaw/ui/deadclaw-button.html:2 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileDeadClaw — WebChat Kill Button Widget A persistent red button for the OpenClaw WebChat dashboard. When clicked, it calls kill.sh via OpenClaw's WebChat API hookFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandscripts/restore.sh:20 · Process kill command — agent can terminate processes# kill event, you want to be sure before bringing things back online.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
HTML comment carrying imperative instructions to the agentui/deadclaw-button.html:2 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileDeadClaw — WebChat Kill Button Widget A persistent red button for the OpenClaw WebChat dashboard. When clicked, it calls kill.sh via OpenClaw's WebChat API hookFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandscripts/watchdog.sh:17 · Process kill command — agent can terminate processes# ./watchdog.sh start --dry-run # Monitor and log but don't auto-killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:4 · Process kill command — agent can terminate processes# Background monitor daemon that auto-triggers the kill script when it detectsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/status.sh:160 · Process kill command — agent can terminate processesif kill -0 "$wpid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/status.sh:228 · Process kill command — agent can terminate processeswarnings+=("Token spend is at ${token_total} — approaching ${max_tokens} kill threshold")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:132 · Process kill command — agent can terminate processes# Trigger the kill script with a reasonFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,505 tok
2 files · 27 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim kintupercy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim kintupercyPropose a patch to the maintainer