Skills/Glama/terminal-mcp

terminal-mcp@0.1.0

CAUTION· install only

Publisher 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.

Registry GlamaPublisher parithosh-varma · publishing for 5 daysInstalls 0Last detonated 5d ago

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.

$vet-skills run --net declared -- <the server's command>

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
References a credential file in the home directoryscripts/smoke.ts:103 · References a credential file in the home directoryconst 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.
AST03
HIGH
Access to sensitive file pathsscripts/smoke.ts:85 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst 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.
AST05
HIGH
Access to sensitive file pathsscripts/smoke.ts:82 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst 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.
AST05
CRITICAL
Reads credential paths from the home directoryscripts/smoke.ts:105 · Reads credential paths from the home directory"kernel sandbox blocks reading ~/.ssh",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
CRITICAL
Reads credential paths from the home directoryscripts/smoke.ts:103 · Reads credential paths from the home directoryconst 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.
AST03
CRITICAL
Reads credential paths from the home directoryscripts/smoke.ts:110 · Reads credential paths from the home directoryconsole.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.
AST03
HIGH
Access to sensitive file pathsscripts/smoke.ts:105 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"kernel sandbox blocks reading ~/.ssh",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/smoke.ts:103 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst 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.
AST05
MEDIUM
Process kill commandscripts/up.sh:56 · Process kill command — agent can terminate processes[[ -n "$AGENT_PID" ]] && kill "$AGENT_PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/lib/osSandbox.ts:70 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".netrc",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Authorization escalation languageREADME.md:175 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file · informational: not an instruction fileIn 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.
AST01
MEDIUM
Process kill commandscripts/up.sh:57 · Process kill command — agent can terminate processes[[ -n "$SERVER_PID" ]] && kill "$SERVER_PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/up.sh:23 · Process kill command — agent can terminate processesif [[ -n "$OLD_PID" ]] && kill -0 "$OLD_PID" 2>/dev/null \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Credential pass-through configurationworker/src/index.ts:32 · Credential pass-through configuration — agent relays sensitive credentials"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.
AST02
MEDIUM
Process kill commandscripts/up.sh:26 · Process kill command — agent can terminate processesecho " Stop it first with: kill $OLD_PID"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injectionREADME.md:175 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction fileIn ChatGPT: **Settings → Connectors → Advanced → Developer mode → Add custom connector**Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File permission modification commandsrc/tools/files.ts:94 · File permission modification command — agent changes file ownership/permissionsexecutable: z.boolean().optional().describe("chmod +x after writing."),Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/up.sh:102 · Process kill command — agent can terminate processeswhile kill -0 "$AGENT_PID" 2>/dev/null; doFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈39 tok
1 file · 48 in bundle

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%
  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. 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.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim parithosh-varmaPropose a patch to the maintainer