Skills/PyPI/mcp-vulnerabilities

mcp-vulnerabilities@1.7.32

CAUTION· not started

Publisher claims: "Open-Source OSV-Compliant Model Context Protocol (MCP) Vulnerability Advisory Database" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 730 daysInstalls 5,814Last detonated 28 min 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
DISCORD_WEBHOOK_URLGH_TOKENGITHUB_TOKENGLAMA_API_KEYNVD_API_KEYSLACK_WEBHOOK_URL or --no-authConfiguration, not credentials: MCP_CACHE_DIR, MCP_VULN_CACHE_DIR
Where it talks to
no vendor host named in the codeAlso githubusercontent.com, osv.dev, nist.gov, jsdelivr.net, shields.io, apple.com, glama.ai, jsonfeed.org, cve.org — 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
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names githubusercontent.com, osv.dev, nist.gov, jsdelivr.net, shields.io, apple.com, glama.ai, jsonfeed.org, cve.org as well as its own vendor. The guard injects DISCORD_WEBHOOK_URL, GH_TOKEN, GITHUB_TOKEN, GLAMA_API_KEY, NVD_API_KEY, SLACK_WEBHOOK_URL only into requests to the host you bind (and its subdomains) and refuses the rest.

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

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.7.17

vet-skills diff mcp-vulnerabilities 1.7.17 1.7.32

In the sandbox, this version reached for nothing 1.7.17 did not. Compared from the two recorded runs, not from source.

1.7.17 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-21 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collects environment variables by secret-like names; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/audit/tui.py:191 · Python subprocess execution detectedp = subprocess.Popen(['xclip', '-selection', 'clipboard'], stdin=subprocess.PIPE, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/audit/tui.py:187 · Python subprocess execution detectedp = subprocess.Popen(['pbcopy'], stdin=subprocess.PIPE, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/audit/tui.py:195 · Python subprocess execution detectedp = subprocess.Popen(['clip'], stdin=subprocess.PIPE, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Collects environment variables by secret-like namessrc/mcp_vulnerabilities/sandbox/drivers.py:41 · Collects environment variables by secret-like namesfor k, v in os.environ.items():Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Access to sensitive file pathssrc/mcp_vulnerabilities/bot/scanner.py:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesIGNORE_DIRS = {".git", "node_modules", ".venv", "venv", "env", ".env", "dist", "build"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/probe/transport.py:111 · Python subprocess execution detectedself.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/discovery/gitlab.py:37 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(repo_dir), "sparse-checkout", "add", eco], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionsrc/mcp_vulnerabilities/cli/parser.py:46 · File type combined with upload action — agent may exfiltrate local data files"--catalog-file", default="data/mcp_servers.json", help="Output catalog path"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/mcp_vulnerabilities/audit/parsers.py:482 · npx invocation of non-well-known package — may execute untrusted code"""Discovers globally installed npm and npx cached MCP servers."""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/discovery/gitlab.py:28 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(repo_dir), "pull", "--rebase"], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/bot/pr_builder.py:28 · Python subprocess execution detectedreturn subprocess.run(cmd, cwd=self.repo_root, capture_output=True, check=check)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 packagesrc/mcp_vulnerabilities/cli/parser.py:305 · npx invocation of non-well-known package — may execute untrusted codeaud_p.add_argument("--global", dest="audit_global", action="store_true", help="Audit globally installed npm/npx MCP packages")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/mcp_vulnerabilities/cli/parser.py:270 · File type combined with upload action — agent may exfiltrate local data files"--output-gz", default="vulnerabilities.json.gz", help="Output gzip file path"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/runner.py:108 · Python subprocess execution detectedresult = subprocess.run(run_cmd, capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/daemon/monitor.py:113 · Python subprocess execution detectedsubprocess.run(["notify-send", title, message, f"--urgency={urgency}"], check=False, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/runner.py:127 · Python subprocess execution detectedsubprocess.run(exec_cmd, capture_output=True, text=True, check=True, timeout=self.timeout)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 packagesrc/mcp_vulnerabilities/audit/parsers.py:312 · npx invocation of non-well-known package — may execute untrusted code"""Discovers and parses MCP configurations across 17 AI clients + global npm/npx packages."""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/daemon/monitor.py:101 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/discovery/gitlab.py:27 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(repo_dir), "reset", "--hard", "origin/main"], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/runner.py:68 · Python subprocess execution detectedsubprocess.run(cmd, capture_output=True, text=True, check=True, timeout=self.timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/engine.py:12 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/runner.py:183 · Python subprocess execution detectedsubprocess.run([self.engine_cmd, "rm", "-f", container_id], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/drivers.py:175 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/engine.py:34 · 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
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/runner.py:87 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/discovery/gitlab.py:34 · Python subprocess execution detectedsubprocess.run(["git", "clone", "--filter=blob:none", "--sparse", self.repo_url, str(repo_dir)], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_vulnerabilities/sandbox/drivers.py:170 · Python subprocess execution detectedsubprocess.run(launch_cmd, check=True, capture_output=True, timeout=timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈62 tok
1 file · 81 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. 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.
  2. Collects environment variables by secret-like names≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  3. 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.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
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