mcp-nexus-sdk@1.3.2
CAUTION· not startedPublisher claims: "Headless Python SDK + CLI for the Nexus skill platform (bundles nexus_core)" 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: Caution 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
MINIMAX_TOKEN_PLAN_KEYNEXUS_API_KEYNEXUS_BUILD_SECRETNEXUS_OFFLINE_SECRETor--llm-api-keyConfiguration, not credentials: __NEXUS_ARGV__, __NEXUS_INPUTS__, __NEXUS_PARAMS__, NEXUS_ALLOW_UNSIGNED_PACKAGES, NEXUS_BUNDLED_PY_VERSION, NEXUS_CHAT_UAT_FIXTURES_DIR, NEXUS_DATA_DIR, NEXUS_DEV_MODE, NEXUS_LLM_URL, NEXUS_PACKAGE_PUBKEY_B64, NEXUS_PYPI_INDEX, NEXUS_PYTHON, NEXUS_SERVER_URL, NEXUS_SKILL_LOG_DIR, NEXUS_SKILLS_DIR, PBS_ASSET_URL- Where it talks to
- no vendor host named in the codeAlso mcp-nexus.online, tsinghua.edu.cn, aliyun.com, ustc.edu.cn, openxmlformats.org — 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 mcp-nexus.online, tsinghua.edu.cn, aliyun.com, ustc.edu.cn, openxmlformats.org as well as its own vendor. The guard injects MINIMAX_TOKEN_PLAN_KEY, NEXUS_API_KEY, NEXUS_BUILD_SECRET, NEXUS_OFFLINE_SECRET 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 2026-11-08 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; OS command execution function call detected; OS command execution function call detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
The JSON-file fallback stores the API key in plaintext (chmod 0600 on POSIX);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f"Pass them via the inputs dict (keys must match skill.json manifest.inputs)."Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proc = subprocess.run(argv, capture_output=True, text=True, timeout=timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._KEY_DECL_RX = re.compile(r"MINIMAX_AGENT_KEY\s*=\s*process\.env\.([A-Z_]+)\s*\|\|\s*'([^']+)'")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose." os.system(cmd)\n",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(argv + ["-i", idx], capture_output=True, text=True, timeout=1800)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.os.system(cmd)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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 mcp-nexus-sdk@1.3.2 as of 6d ago. This is the package itself, not its dependencies.
What would make this Verified
7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim mcp-nexus: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.