Skills/PyPI/shellsage-mcp

shellsage-mcp@0.3.1

CAUTION· not started

Publisher claims: "Shell command translation layer for AI agent IDEs — no external services required." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher shellsage · publishing for 142 daysInstalls 60Last detonated 2 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 codeAlso python.org, microsoft.com, httpbin.org, man7.org, ss64.com, curl.se, gnu.org, git-scm.com, docker.com, kubernetes.io, yarnpkg.com, pypa.io, nodejs.org, rust-lang.org, go.dev — not the publisher's domain; check what for before connecting.
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 shellsage-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 2026-11-18 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Privileged sudo command; Access to sensitive file paths. 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

HIGH
Access to sensitive file pathsshellsage/seed.py:135 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"bash": "cat .env", "ps": "Get-Content '.env'"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedshellsage/models.py:204 · Python subprocess execution detectedsubprocess.run([cmd, "--version"], capture_output=True, timeout=2)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandshellsage/seed.py:498 · Privileged sudo command — agent may execute with elevated privileges{"bash": "sudo command", "ps": "# Run PowerShell as Administrator, then: command"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandshellsage/rules.py:615 · File permission modification command — agent changes file ownership/permissions"# chmod not available in PowerShell — use icacls for ACL management",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedshellsage/models.py:196 · Python subprocess execution detectedresult = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=3)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsshellsage/seed.py:200 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"bash": "cp .env .env.example", "ps": "Copy-Item '.env' '.env.example'"},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 pathsshellsage/seed.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"bash": "find . -name '.env'", "ps": "Get-ChildItem -Recurse -Filter '.env' -Force"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedshellsage/daemon.py:133 · Python subprocess execution detectedproc = subprocess.Popen(cmd, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
README links to an external installerREADME.md → https://example.com/a.ziphttps://example.com/a.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedshellsage/daemon.py:150 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandshellsage/rules.py:610 · File permission modification command — agent changes file ownership/permissionslambda m: f"# chmod +x not needed in PowerShell — rename to '{m.group(1).strip().replace('.sh', '.ps1')}' or use Set-ExecutionPolicy",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandshellsage/seed.py:479 · File permission modification command — agent changes file ownership/permissions"bash": "chmod +x script.sh",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionshellsage/seed.py:682 · File type combined with upload action — agent may exfiltrate local data files{"bash": "tee output.txt", "ps": "Tee-Object -FilePath 'output.txt'"},Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionshellsage/seed.py:185 · File type combined with upload action — agent may exfiltrate local data files{"bash": "rm output.log", "ps": "Remove-Item 'output.log'"},Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandtests/test_rules.py:172 · Process kill command — agent can terminate processesresult = ps("kill -9 1234")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandshellsage/seed.py:484 · File permission modification command — agent changes file ownership/permissions"ps": "# chmod not needed in PowerShell — use .ps1 files or Set-ExecutionPolicy",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packageshellsage/seed.py:629 · npx invocation of non-well-known package — may execute untrusted code{"bash": "npx tsc", "ps": "npx tsc"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedshellsage/setup_wizard.py:57 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandshellsage/rules.py:620 · File permission modification command — agent changes file ownership/permissions"# chown not available in PowerShell — use icacls: icacls <path> /setowner <user>",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandshellsage/seed.py:330 · Process kill command — agent can terminate processes{"bash": "kill 1234", "ps": "Stop-Process -Id 1234"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionshellsage/seed.py:187 · File type combined with upload action — agent may exfiltrate local data files{"bash": "rm -f output.log", "ps": "Remove-Item -Force 'output.log'"},Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionshellsage/seed.py:274 · File type combined with upload action — agent may exfiltrate local data files"ps": "Import-Csv 'data.csv' | Select-Object -ExpandProperty (Get-Member -InputObject (Import-Csv 'data.csv' | Select-Object -First 1) -MemberType NoteProperty).Name[1]",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandshellsage/seed.py:483 · File permission modification command — agent changes file ownership/permissions"bash": "chmod 755 script.sh",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandshellsage/seed.py:487 · File permission modification command — agent changes file ownership/permissions"bash": "chmod -R 755 dir/",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionshellsage/seed.py:713 · File type combined with upload action — agent may exfiltrate local data files{"bash": "command > output.txt 2>&1", "ps": "command > 'output.txt' 2>&1"},Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Destructive file system command detectedtests/test_rules.py:111 · Destructive file system command detected# ── mkdir / rm / cp / mv ──────────────────────────────────────────────────────Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageshellsage/seed.py:628 · npx invocation of non-well-known package — may execute untrusted code{"bash": "npx create-react-app myapp", "ps": "npx create-react-app myapp"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandshellsage/seed.py:480 · File permission modification command — agent changes file ownership/permissions"ps": "# chmod not needed in PowerShell — use .ps1 files or Set-ExecutionPolicy",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandshellsage/seed.py:329 · Process kill command — agent can terminate processes{"bash": "kill -9 1234", "ps": "Stop-Process -Id 1234 -Force"},Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈57 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 shellsage-mcp@0.3.1 as of 1 h ago. This is the package itself, not its dependencies.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim shellsage: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +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 shellsagePropose a patch to the maintainer