claw-mission-killer@0.1.0
VERIFIED· install onlyPublisher claims: "Interrupt a running agent task and rollback its session to the state before the last triggering user message. Use when an agent is stuck, running the wrong t..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-16 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenariosStatic findings
result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(["ps", "aux"], capture_output=True, text=True, timeout=10)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Risk: Install and watcher scripts can persistently append protocol text to AGENTS.md files and alter future agent behavior.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.print("[interrupt] DRY-RUN: would kill PID tree")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Clear marker after killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.scripts directly to enable precise kill support.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill allFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…nt", "stop agent and rollback", "cut agent task", "terminate and reset agent", "kill my_agent", "kill all agents", "终止 agent 任务并回滚", "kill掉", "打断". Supports all conf…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.Popen(cmd_args)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.kill dev1 → matches zero_dev1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.This enables precise kill support via the agent-interrupt skill.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.This allows agent-interrupt to precisely kill the correct process.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.This enables precise kill support via the agent-interrupt skill.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill dev1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Priority 1: Use running.json marker for precise killFix: 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.