Skills/PyPI/mcpfuzz

mcpfuzz@0.1.4

CAUTION· not started

Publisher claims: "Dynamic security scanner for MCP (Model Context Protocol) servers — actively probes live servers with exploit payloads" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher cyberneticsplus-services · publishing for 226 daysInstalls 27Last 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 codeAlso evil.com, attacker.local, google.internal, ollama.com — 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 mcpfuzz

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 2026-11-11 and scored it 68/100 (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; OS command execution function call detected; 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 pathssrc/mcpfuzz/modules/path_traversal.py:32 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
OS command execution function call detectedsrc/mcpfuzz/utils/sast_scanner.py:87 · OS command execution function call detected"os.system() — direct shell command execution",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/command_injection.py:58 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesre.compile(r"root:.*:/bin/(bash|sh)"), # /etc/passwd root entryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/cve_checks.py:84 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Classic prefix collision: /tmp is allowed, /tmpevil/../etc/passwd bypasses checkFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/path_traversal.py:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"../../../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 pathssrc/mcpfuzz/modules/cve_checks.py:86 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("/tmpevil/../etc/passwd", "Prefix collision: /tmpevil/../etc/passwd"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Cross-server tool referencesrc/mcpfuzz/modules/cve_checks.py:590 · Cross-server tool reference — agent may chain tools across untrusted MCP serversf"tools with generic names from different servers can shadow each other, "Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
CRITICAL
URL to the cloud instance metadata addresssrc/mcpfuzz/modules/ssrf.py:106 · URL to the cloud instance metadata address — reads the VM's credentials("AWS EC2 IAM Credentials", "http://169.254.169.254/latest/meta-data/iam/security-credentials/", "AWS IAM credentials exposure"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/cve_checks.py:88 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("/tmp/../../etc/passwd", "Double traversal from allowed base"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
URL to the cloud instance metadata addresssrc/mcpfuzz/modules/ssrf.py:108 · URL to the cloud instance metadata address — reads the VM's credentials("Azure IMDS", "http://169.254.169.254/metadata/instance?api-version=2021-02-01", "Azure managed identity exposure"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/cve_checks.py:87 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("/tmp/../etc/passwd", "Parent traversal from allowed base"),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 pathssrc/mcpfuzz/modules/command_injection.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"; cat /etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
URL to the cloud instance metadata addresssrc/mcpfuzz/modules/ssrf.py:105 · URL to the cloud instance metadata address — reads the VM's credentials("AWS EC2 Metadata", "http://169.254.169.254/latest/meta-data/", "AWS IAM credentials exposure"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
CRITICAL
URL to the cloud instance metadata addresssrc/mcpfuzz/modules/dns_rebinding.py:23 · URL to the cloud instance metadata address — reads the VM's credentials"http://169.254.169.254",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-wave1.sh:128 · npx invocation of non-well-known package — may execute untrusted codescan_target "T0221" "4609" "@21st-dev/magic" "npx -y @21st-dev/magic" 3Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpfuzz/modules/cve_checks.py:149 · npx invocation of non-well-known package — may execute untrusted code"pnpm dlx", "pnpm exec", # pnpm equivalents of npxFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpfuzz/modules/cve_checks.py:144 · npx invocation of non-well-known package — may execute untrusted code"npx ", "npx\t", # npm package runner (most common)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch2.sh:165 · npx invocation of non-well-known package — may execute untrusted code"npx -y mcp-mongo-server mongodb://localhost:27017"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch1.sh:127 · npx invocation of non-well-known package — may execute untrusted code"npx -y mcp-postgres $PG_URL"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Hex-encoded URLsrc/mcpfuzz/modules/ssrf.py:116 · Hex-encoded URL — attempt to bypass URL filtering("Hex IP Localhost", "http://0x7f000001/", "IP obfuscation bypass"),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-wave1.sh:130 · npx invocation of non-well-known package — may execute untrusted codescan_target "T0234" "1605" "tavily-mcp" "npx -y tavily-mcp" 5Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-wave1.sh:127 · npx invocation of non-well-known package — may execute untrusted codescan_target "T0213" "6585" "cursor-talk-to-figma-mcp" "npx -y cursor-talk-to-figma-mcp" 2Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/path_traversal.py:36 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injection attemptdocs/modules.md:186 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file- Prompt injection patterns: `ignore previous instructions`, `disregard`, `you are now`, `system prompt override`, `<SYSTEM>`, etc.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-wave1.sh:129 · npx invocation of non-well-known package — may execute untrusted codescan_target "T0228" "2063" "@perplexity-ai/mcp-server" "npx -y @perplexity-ai/mcp-server" 4Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch2.sh:108 · npx invocation of non-well-known package — may execute untrusted code"npx -y @liangshanli/mcp-server-redis" \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Fake instruction boundary tagdocs/modules.md:186 · Fake instruction boundary tag · informational: not an instruction file- Prompt injection patterns: `ignore previous instructions`, `disregard`, `you are now`, `system prompt override`, `<SYSTEM>`, etc.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch1.sh:119 · npx invocation of non-well-known package — may execute untrusted code"npx -y mcp-postgres-full-access" \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch1.sh:123 · npx invocation of non-well-known package — may execute untrusted code"npx -y mcp-postgres-server" \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-wave1.sh:126 · npx invocation of non-well-known package — may execute untrusted codescan_target "T0202" "40331" "@chakra-ui/react-mcp" "npx -y @chakra-ui/react-mcp" 1Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch1.sh:113 · npx invocation of non-well-known package — may execute untrusted code"npx -y @bytebase/dbhub --transport stdio --dsn \"$PG_URL2\""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpfuzz/modules/cve_checks.py:150 · npx invocation of non-well-known package — may execute untrusted code"yarn dlx", # yarn equivalent of npxFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch2.sh:104 · npx invocation of non-well-known package — may execute untrusted code"npx -y mcp-redis-diagnostics" \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch2.sh:101 · npx invocation of non-well-known package — may execute untrusted code"npx -y @modelcontextprotocol/server-redis redis://localhost:6379"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/path_traversal.py:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"../../../../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch2.sh:162 · npx invocation of non-well-known package — may execute untrusted code"npx -y mongodb-mcp-server --connectionString mongodb://localhost:27017"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcpfuzz/utils/sast_scanner.py:9 · npx invocation of non-well-known package — may execute untrusted code- `npx [-y] PACKAGE [args]`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Dense URL-encoded contentsrc/mcpfuzz/modules/path_traversal.py:39 · Dense URL-encoded content — may be obfuscating payloads"%2e%2e%2f%2e%2e%2fetc%2fpasswd",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathssrc/mcpfuzz/modules/path_traversal.py:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"../../../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/mcpfuzz-docker-batch1.sh:107 · npx invocation of non-well-known package — may execute untrusted code"npx -y @modelcontextprotocol/server-postgres $PG_URL"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈63 tok
1 file · 45 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 mcpfuzz@0.1.4 as of 4d ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. URL to the cloud instance metadata address≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Unclaimed publisher≈ +8 on the totalClaim cyberneticsplus-services: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  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. Cross-server tool reference≈ +4 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
  6. Hex-encoded URL≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cyberneticsplus-servicesPropose a patch to the maintainer