deadclaw@1.0.1
CAUTION· static onlyPublisher 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.
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 onlyThis 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
Emergency kill switch for OpenClaw agents. Instantly halts all running agents,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# ./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.# Post-kill recovery script. Restores the backed-up crontab and optionallyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# 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.# 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.button, deadclaw, agent safety, runaway agent, kill all, stop everything, or anyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.warnings+=("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.# Core emergency kill script for OpenClaw agents.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.the user mentions: emergency stop, kill switch, stop agents, halt agents, panicFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.warnings+=("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.# Graceful: kill sessions inside the container firstFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# ./kill.sh # Execute the killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.log_event "DRY-RUN: Would kill PID $pid ($(ps -p "$pid" -o comm= 2>/dev/null || echo 'unknown'))"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.the user mentions: emergency stop, kill switch, stop agents, halt agents, panicFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.SCREENSHOT_PLACEHOLDER: test-run-result.pngFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.DeadClaw is a single-purpose emergency kill switch. When triggered, it immediatelyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.DeadClaw is a single-purpose emergency kill switch. When triggered, it immediatelyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.button, deadclaw, agent safety, runaway agent, kill all, stop everything, or anyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Emergency kill switch for OpenClaw agents. Instantly halts all running agents,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.SCREENSHOT_PLACEHOLDER: test-run-result.pngFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.if kill -0 "$wpid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "$watchdog_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Graceful: kill sessions inside the container firstFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# ./kill.sh --dry-run # Log what would happen, don't kill anythingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Core emergency kill script for OpenClaw agents.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# ./kill.sh # Execute the killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "$existing_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Post-kill recovery script. Restores the backed-up crontab and optionallyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# 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.# ./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.log_event "DRY-RUN: Would kill PID $pid ($(ps -p "$pid" -o comm= 2>/dev/null || echo 'unknown'))"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Trigger the kill script with a reasonFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "$watchdog_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# 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.# 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.warnings+=("Agent ${agent_names[$i]} (PID ${agent_pids[$i]}) has been running ${agent_uptimes[$i]} — approaching ${max_runtime}min kill threshold")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "$existing_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.DeadClaw — 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.# 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.DeadClaw — 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.# ./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.# 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.if kill -0 "$wpid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.warnings+=("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.# Trigger the kill script with a reasonFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
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%- 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.
- 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.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.