terminal-mcp@0.1.0
CAUTION· install onlyPublisher claims: "Enables Claude and ChatGPT to run sandboxed shell commands, manage files and Git, search code, and use system/network tools within a kernel-enforced, per-session workspace jail that blocks access to credentials and files outside the sandbox." 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: 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
CLOUDFLARE_API_TOKENMY_APP_SECRETRELAY_TOKENTERMINAL_MCP_TOKENConfiguration, not credentials: RELAY, RELAY_LOCAL, RELAY_NAME, RELAY_URL, RELAY_VERBOSE, SMOKE_NPM, TERMINAL_MCP_ALLOW_INSECURE, TERMINAL_MCP_HOME, TERMINAL_MCP_HOST, TERMINAL_MCP_JSON_RESPONSE, TERMINAL_MCP_MAX_OUTPUT, TERMINAL_MCP_NETWORK, TERMINAL_MCP_PORT, TERMINAL_MCP_READ_PATHS, TERMINAL_MCP_ROOT, TERMINAL_MCP_SANDBOX, TERMINAL_MCP_SHARED, TERMINAL_MCP_STATE, TERMINAL_MCP_TIMEOUT_MS, TERMINAL_MCP_WRITE_PATHS- Where it talks to
- no vendor host named in the codeAlso workers.dev, pages.dev, ipinfo.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 workers.dev, pages.dev, ipinfo.io as well as its own vendor. The guard injects CLOUDFLARE_API_TOKEN, MY_APP_SECRET, RELAY_TOKEN, TERMINAL_MCP_TOKEN 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: References a credential file in the home directory; 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 · 0 s · 1 scenarios · 0 deviationsStatic findings
const ssh = await call("run_command", { command: "cat ~/.ssh/id_ed25519 ~/.ssh/id_rsa 2>&1 | head -2" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const absolute = await call("read_file", { path: "/etc/passwd" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const escape = await call("read_file", { path: "../../etc/passwd" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."kernel sandbox blocks reading ~/.ssh",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const ssh = await call("run_command", { command: "cat ~/.ssh/id_ed25519 ~/.ssh/id_rsa 2>&1 | head -2" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(" SKIP ~/.ssh read denial (no ~/.ssh on this machine)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."kernel sandbox blocks reading ~/.ssh",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const ssh = await call("run_command", { command: "cat ~/.ssh/id_ed25519 ~/.ssh/id_rsa 2>&1 | head -2" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.[[ -n "$AGENT_PID" ]] && kill "$AGENT_PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.".netrc",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.In ChatGPT: **Settings → Connectors → Advanced → Developer mode → Add custom connector**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.[[ -n "$SERVER_PID" ]] && kill "$SERVER_PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if [[ -n "$OLD_PID" ]] && kill -0 "$OLD_PID" 2>/dev/null \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."Unauthorized. Provide the relay token as ?token=…, an Authorization: Bearer header, " +Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo " Stop it first with: kill $OLD_PID"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.In ChatGPT: **Settings → Connectors → Advanced → Developer mode → Add custom connector**Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.executable: z.boolean().optional().describe("chmod +x after writing."),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.while kill -0 "$AGENT_PID" 2>/dev/null; doFix: 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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Reads credential paths from the home directory≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim parithosh-varma: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.