Skills/PyPI/mcp-yieldshell

mcp-yieldshell@1.1.2

CAUTION· not started

Publisher claims: "A drop-in shell MCP that auto-yields long-running commands into managed background executions." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 723 daysInstalls 329Last detonated 4d ago
What would fix thisWatchDispute verdict

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 the honeypot saw
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 mcp-yieldshell

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 2026-11-10 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; 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
Python subprocess execution detectedtests/test_lifecycle_hardening.py:361 · Python subprocess execution detectedf"{sys.executable} -c \"import subprocess; subprocess.Popen(['sleep','30'])\"",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_integration.py:257 · Python subprocess execution detected"python -c \"import subprocess; subprocess.Popen([\\\"sleep\\\", \\\"30\\\"])\"",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/mcp_yieldshell/server.py:224 · Process kill command — agent can terminate processes"""Stop a running execution, escalating to force kill when needed.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_release.py:80 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/mcp_yieldshell/execution/manager.py:900 · Process kill command — agent can terminate processes# Force kill any children that survived graceful termination, even ifFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_lifecycle_hardening.py:731 · Python subprocess execution detectedf"subprocess.Popen(['{sys.executable}','-c',"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternsrc/mcp_yieldshell/side_effects.py:33 · Pipe-to-shell pattern — downloads and immediately executes remote code"(e.g. python -c, node -e, curl ... | sh); create or edit a "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedtests/test_lifecycle_hardening.py:709 · Python subprocess execution detected"subprocess.Popen(['sleep','30'])\"",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_release.py:74 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternsrc/mcp_yieldshell/types.py:28 · Pipe-to-shell pattern — downloads and immediately executes remote code``curl ... | sh``. It does not cover simply creating a script orFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedtests/test_release.py:68 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedtests/test_integration.py:800 · Destructive file system command detectedresult = await mgr.execute_command("rm -rf /tmp/test", side_effects=NONE)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_lifecycle_hardening.py:517 · Python subprocess execution detected"subprocess.Popen(['sleep','30']); time.sleep(30)\"",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsrc/mcp_yieldshell/types.py:28 · Remote installer piped to shell``curl ... | sh``. It does not cover simply creating a script orFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedtests/test_lifecycle_hardening.py:382 · Python subprocess execution detectedf"{sys.executable} -c \"import subprocess; subprocess.Popen(['sleep','30'])\"",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsrc/mcp_yieldshell/server.py:76 · Remote installer piped to shell``curl ... | sh``). It does not cover simply creating a script orFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedtests/test_release.py:92 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedtests/test_config.py:135 · Destructive file system command detectedassert config.deny_command_regex.search("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontests/test_release.py:371 · File type combined with upload action — agent may exfiltrate local data files["git", "add", "unrelated.txt"], cwd=repo, check=True, capture_output=TrueFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellsrc/mcp_yieldshell/side_effects.py:33 · Remote installer piped to shell"(e.g. python -c, node -e, curl ... | sh); create or edit a "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Process kill commandsrc/mcp_yieldshell/execution/spawn.py:76 · Process kill command — agent can terminate processes"""Force kill the process group."""Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_release.py:381 · File type combined with upload action — agent may exfiltrate local data files["git", "add", "unrelated.txt"], cwd=repo, check=True, capture_output=TrueFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Destructive command against a filesystem root or devicetests/test_config.py:135 · Destructive command against a filesystem root or deviceassert config.deny_command_regex.search("rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_release.py:86 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternsrc/mcp_yieldshell/server.py:76 · Pipe-to-shell pattern — downloads and immediately executes remote code``curl ... | sh``). It does not cover simply creating a script orFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Process kill commandsrc/mcp_yieldshell/execution/manager.py:1138 · Process kill command — agent can terminate processes# Reserve time for force-kill observation, final drain, and subprocessFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_security.py:21 · Destructive command against a filesystem root or deviceassert validate_command(config, "rm -rf /") is NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_security.py:26 · Destructive command against a filesystem root or deviceerror = validate_command(config, "rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_security.py:21 · Destructive file system command detectedassert validate_command(config, "rm -rf /") is NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_security.py:26 · Destructive file system command detectederror = validate_command(config, "rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈61 tok
1 file · 27 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 mcp-yieldshell@1.1.2 as of 4d 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 pypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pypiPropose a patch to the maintainer