n1mem-mcp@0.6.0
VERIFIED· install onlyPublisher claims: "N1Mem MCP server (BYOK, zero dependencies) — long-term memory for Claude / Cursor / OpenClaw, including one-call import of your existing agent memory and local value telemetry (~/.n1mem/events.jsonl)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
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
N1MEM_API_KEYConfiguration, not credentials: N1MEM_AGENT_ID, N1MEM_BASE_URL, N1MEM_DEVICE_ID, N1MEM_HOME, N1MEM_INSTANCE, N1MEM_MCP_RETRIES, N1MEM_MCP_RETRY_BACKOFF, N1MEM_MCP_TIMEOUT, N1MEM_SUBJECT, N1MEM_TELEMETRY, N1MEM_TELEMETRY_MAX_MB, N1MEM_TELEMETRY_PREVIEW- Where it talks to
- n1mem.com (its own)Also microsoft.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
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names microsoft.com as well as its own vendor. The guard injects N1MEM_API_KEY only into requests to n1mem.com (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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 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 · 1 scenarios · 0 deviationsStatic findings
r = subprocess.run(["schtasks", "/Query", "/TN", name, "/FO", "LIST", "/V"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([exe, "-c", "import sys;print(sys.version_info[0])"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# （只有个别的事备份任务），而安装时是传了 enable_autoupdate=True 的。Fix: Pin versions and sources; vendor anything fetched at install time.subprocess.run(["schtasks", "/Delete", "/TN", spec.name, "/F"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["schtasks", "/Create", "/TN", spec.name, "/XML", str(tmp), "/F"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["schtasks", "/Query", "/TN", name, "/XML"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.n1mem-autoupdate Execute = D:\\Project\\...\\.venv\\Scripts\\python.exe ← 开发机的 venvFix: Pin versions and sources; vendor anything fetched at install time.r = subprocess.run(_argv,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([py, "-m", "pip", "install", f"{pkg}>={MIN_VERSIONS[pkg]}"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([sys.executable, str(updater), "--json"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([py, "-c", code], capture_output=True, text=True, encoding="utf-8", timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([py, "-m", "pip", "install", "-U", pkg],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([py, "-m", "pip", "show", p], capture_output=True, text=True, encoding="utf-8", timeout=60)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. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for n1mem-mcp@0.6.0 as of 6d ago. This is the package itself, not its dependencies.