vulcai-mcp-forge-cli@0.4.4
CAUTION· install onlyPublisher claims: "Generate MCP servers instantly from any OpenAPI, GraphQL, codebase, CLI or website" 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 57 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: 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_KEYBEARER_TOKENFORGE_LICENSE_KEYGROQ_API_KEYConfiguration, not credentials: _MCP_SMOKE_PATH, FORGE_API_URL, FORGE_BUILD_COMMIT, FORGE_MODE, GROQ_MODEL, LLM_BASE_URL, LLM_MODEL, MCP_FORGE_EVAL_MODEL, MCP_FORGE_EVAL_PROVIDER, MCP_FORGE_STATIC_ANALYZERS- Where it talks to
- no vendor host named in the codeAlso swagger.io, groq.com, evil.example, other-server.example, nodejs.org, test.example, mistral.ai, claude.com, vulcai.io — 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 swagger.io, groq.com, evil.example, other-server.example, nodejs.org, test.example, mistral.ai, claude.com, vulcai.io as well as its own vendor. The guard injects ANTHROPIC_API_KEY, BEARER_TOKEN, FORGE_LICENSE_KEY, GROQ_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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 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: Collects environment variables by secret-like names; 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
env = {k: v for k, v in os.environ.items() if not _SECRET_ENV.search(k)}Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = subprocess.run(command, cwd=str(server_dir), env=_inspector_env())Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r"(~/\.ssh|\.ssh/|\bid_rsa\b|\bid_ed25519\b|~/\.aws|/etc/passwd|/etc/shadow|\bmcp\.json\b|"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_path = Path.cwd() / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own." (Run again from the folder that holds your .env)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Set ANTHROPIC_API_KEY or GROQ_API_KEY in your .env."Fix: 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.Saves the license key to the .env file of the current folder.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run([sys.executable, "-I", "-c", loader], cwd=tmp, env=env,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.load_dotenv(Path.cwd() / ".env") # Charge .env depuis le dossier de travail de l'utilisateurFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose." → Cloud mode : set FORGE_LICENSE_KEY in your .env\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.print("[red][FAIL] npx not found:[/red] install Node.js (https://nodejs.org) to run MCP Inspector.")Fix: Pin versions and sources; vendor anything fetched at install time.proc = subprocess.run(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.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen([sys.executable, "-I", "-W", "ignore", str(_RUNNER), str(config)], **kwargs)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.r"claude_desktop_config|~/\.config|~/\.netrc|\.env file)", re.I)),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if importlib.util.find_spec("bandit") is None:Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.env.update({"MCP_SERVER_TOKEN": token, "MCP_SERVER_URL": "https://mcp.test.example",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."module = importlib.util.module_from_spec(spec)\n"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."""Commande MCP Inspector (npx + uv), ou None si npx est introuvable.Fix: Pin versions and sources; vendor anything fetched at install time.# (workflow « CLI · test multi-plateforme »). Sans version, npx prendrait laFix: Pin versions and sources; vendor anything fetched at install time.npx est résolu en chemin complet et lancé sans shell. Sous Windows, onFix: Pin versions and sources; vendor anything fetched at install time.module = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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 vulcai-mcp-forge-cli@0.4.4 as of 52 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 vulcai-io: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Collects environment variables by secret-like names≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.