tokeven@0.18.0
CAUTION· not startedPublisher claims: "Privacy first cost visibility for Claude, ChatGPT, Gemini, and Grok (xAI) API calls. Metrics only: your provider keys and prompt content never reach Tokeven." 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
ANTHROPIC_API_KEYXAI_API_KEYor--max-tokens/--cached-tokensConfiguration, not credentials: CLAUDE_TIER, TOKEVEN_AUTO_INSTRUMENT, TOKEVEN_BASE_URL, TOKEVEN_BUDGET_ACTION, TOKEVEN_BUDGET_PER, TOKEVEN_BUDGET_USD, TOKEVEN_GUARD_STATE_DIR, TOKEVEN_LEDGER_DIR, TOKEVEN_LOCAL_LEDGER, TOKEVEN_PLAN, TOKEVEN_QUIET, TOKEVEN_STATUSLINE_CACHE- Where it talks to
- tokeven.com (its own)Also x.ai — 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 x.ai as well as its own vendor. The guard injects ANTHROPIC_API_KEY, XAI_API_KEY only into requests to tokeven.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; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 75/100 (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; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
"""``(value, file)`` for a ``TOKEVEN_*`` key in ./.env.local or ./.env, else None."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose." --env-file PATH Env file to write (default: .env.local in a Next.js\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if env_path.name in patterns or ".env*" in patterns or "*.env" in patterns:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Load settings from the environment (and optional ``.env``)."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.`.env.local` when it already exists or the project is Next.js: Next.js readsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.model_config = SettingsConfigDict(env_file=".env", extra="ignore")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.``TOKEVEN_*`` lines in ``./.env.local`` or ``./.env`` (where ``tokeven init``Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."(pass api_key=... or set ANTHROPIC_API_KEY). Tokeven never sees it."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.`.env.local` ahead of `.env`, so writing `.env` beside an existingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from environment variables (or a local ``.env``) via ``pydantic-settings``.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.tokeven init --env-file config/.env --base-url http://localhost:8000Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose._DOTENV_FILES = (".env.local", ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose." project or where one exists, otherwise .env)\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.runpy.run_path(args[0], run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.runpy.run_module(args[1], run_name="__main__", alter_sys=True)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.(tmp_path / ".env").write_text("TOKEVEN_INGEST_TOKEN=tkv_ing_env\n")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.) # PID reused by something else -- never kill itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.(tmp_path / ".env").write_text(Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return str(env["TOKEVEN_INGEST_TOKEN"]), f"{path} (mcpServers.{name}.env)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Warn-then-kill an idle session, verifying process identity first."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.dropping events. Crash window: a hard kill (SIGKILL, ``os._exit``, power loss)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."""`tokeven init` writes .env; the SDK must pick it up with no extra step."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.except Exception as exc: # noqa: BLE001 - never kill the senderFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."""Real environment > .env.local > .env."""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.shell before wiring the Idle Reaper's kill path to it in production.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.Popen(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 tokeven@0.18.0 as of 7 min ago. This is the package itself, not its dependencies.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim tokeven-team: 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.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Dynamic module loading≈ +1 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.