subtask-mcp@0.5.9
VERIFIED· not startedPublisher claims: "Background sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP or CLI, with a spend cap" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
TYPESAFE_API_KEYConfiguration, not credentials: KIMI_CODE_HOME, SUBTASK_DSH_KEY_FILE, SUBTASK_ENV_FILE, SUBTASK_GROUP_TICK_S, SUBTASK_HOME, SUBTASK_JEV_CONFIG, SUBTASK_JEV_KEY_FILE, SUBTASK_JOB_RETENTION_DAYS, SUBTASK_LIMITS_FILE, SUBTASK_OPENAI_ADMIN_KEY_FILE, SUBTASK_OPENAI_CODEX_HOME, SUBTASK_OPENAI_EFFORT, SUBTASK_OPENAI_MODEL, SUBTASK_PROGRESS_HEARTBEAT_S, SUBTASK_PROGRESS_MIN_S, SUBTASK_RETRY_SLOT_WAIT_S, SUBTASK_ROUTING, SUBTASK_STALL_S, SUBTASK_TELEMETRY_DAYS- Where it talks to
- no vendor host named in the codeAlso kimi.ai, kimi.com, typesafe.ai, deepseek.com, chatgpt.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names kimi.ai, kimi.com, typesafe.ai, deepseek.com, chatgpt.com as well as its own vendor. The guard injects TYPESAFE_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-19 and scored it 85/100 (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 scenarios · 0 deviationsStatic findings
done = subprocess.run(["git", "-C", root, *args], capture_output=True, text=True, timeout=30, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._fake_cli(tmp_path, "kimi", 'env | grep -c -E "GITHUB_TOKEN|ANTHROPIC" ; exit 0')Fix: Never read or enumerate credential locations; accept a documented environment variable instead.entry = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.child = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.blob = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.fake_cli(home, "kimi", 'env | grep -c -E "SOME_RANDOM_VAR|GITHUB_TOKEN|ANTHROPIC" ; exit 0')Fix: Never read or enumerate credential locations; accept a documented environment variable instead.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.child = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([*g, "init", "-q"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(["bun", str(script)], capture_output=True, text=True, timeout=60, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.exec(compile(merged, "m.py", "exec"), {"__name__": "__main__"}) # noqa: S102 - NameError: h defined after mainFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.sentinel = real_popen([sys.executable, "-c", "import time; time.sleep(30)"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(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.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.left = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = real_popen([sys.executable, "-c", "import time; time.sleep(30)"], **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(["git", "-C", sp["repo"], "worktree", "remove", item["worktree"]],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.subprocess.run([*GIT, "-C", str(path), *cmd], check=True)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.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([*g, "commit", "-qm", "root"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([*g, "add", "."], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["kill", "-9", "--", f"-{pid}"], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(["bun", str(script)], capture_output=True, text=True, timeout=60, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.made = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.child = subprocess.Popen([sys.executable, "-c", "pass"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "-m", "subtask.cli", "board", "--json"], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sleeper = subprocess.Popen(["sleep", "30"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.dirty = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(argv, stdin=subprocess.PIPE, stdout=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.auto_review.subprocess, "Popen", lambda *args, **kw: real_popen([sys.executable, "-c", "pass"], **kw)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen([sys.executable, "-c", "pass"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return real_popen(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.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "-I", str(script)], input='{"tool_name": "Bash"}', capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.for ref, why in (("file:../etc/passwd", "outside"), ("file:nope.py", "no such file"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q", str(repo)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", str(repo), "add", "file"], check=True)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.subprocess.run(["git", "init", "-q", str(repo)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run([sys.executable, "-m", "subtask.cli", *args], env=env, capture_output=True,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.# Keep it chmod 600; it is read by the worker only, never returned by a tool.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."url": "https://user:[email protected]/x",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run([sys.executable, "-m", "subtask.cli", *args, "--json", "--no-plugin"], env=e,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.dead = subprocess.Popen([sys.executable, "-c", "pass"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.run = lambda *a, **k: subprocess.run(a, check=True, capture_output=True, text=True, timeout=600, **k)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-C", spec["cwd"], "rm", "-q", "--cached", "tests/edge.sh"], check=True)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.subprocess.run(["git", "-C", str(repo), "add", "."], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.later = subprocess.run(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.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.dead = subprocess.Popen([sys.executable, "-c", "pass"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return importlib.util.find_spec(module) is not NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.assert jobs.status(job)["state"] == "running" # a label, never a killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.self.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "-I", str(script)], input=json.dumps(event), capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q", str(repo)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([*GIT, "-C", str(repo), "commit", "-qam", f"c{i}"], check=True)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.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for subtask-mcp@0.5.9 as of 2 h ago. This is the package itself, not its dependencies.