usmartsg-mcp@1.1.0
VERIFIED· install onlyPublisher claims: "Local MCP server for uSmart SG trading with user-owned credentials and a read-only safety mode" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 19 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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
USMART_OAUTH_SKIP_LISTENERor--allow-unauthenticated-httpConfiguration, not credentials: USMART_HOME, USMART_HOST, USMART_LOG_LEVEL, USMART_MULTIUSER, USMART_OPENAI_CHALLENGE, USMART_PORT, USMART_PROFILE, USMART_READONLY, USMART_RESOURCE_SERVER, USMART_TRANSPORT, USMART_TRUST_ENV- Where it talks to
- usmartsg.com (its own)Also claude.ai, usmartglobal.com, usmart.sg — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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 claude.ai, usmartglobal.com, usmart.sg as well as its own vendor. The guard injects USMART_OAUTH_SKIP_LISTENER only into requests to usmartsg.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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 82/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
from .credentials import CredentialErrorFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .credentials import CredentialError, CredentialStoreFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .credentials import OAuthConfigFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .credentials import Credentials, CredentialStoreFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.from .credentials import OAuthConfig, ResourceServerConfigFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r"(^|/)(credentials\.json|config\.json|oauth_session\.json|\.env|.*\.pem|.*\.key|.*\.p12|.*\.pfx)$"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.module = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.from .credentials import CredentialStoreFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f"凭证文件权限过宽: {path}(当前 {oct(mode)}),请执行 chmod 600 {path}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .credentials import CONFIG_FILE, CredentialError, CredentialStoreFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from ..credentials import MultiUserConfig, OAuthConfigFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .credentials import Credentials, CredentialStoreFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f"OAuth 会话文件权限过宽:{path}(当前 {oct(mode)}),请执行 chmod 600 {path}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.未配置时生成 ``broker.key`` 文件并 chmod 600;Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.f"请执行 chmod 700 {self._base_dir}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 usmartsg-mcp@1.1.0 as of 8 min ago. This is the package itself, not its dependencies.