Skip to content

ATK Security Checks

by atkvn.com · remote · no sign-in to list tools · v0.1.0 · published by com.atkvn

Post-quantum TLS and certificate checks, plus a Wazuh audit for rules that pass -t but never load.

Changes · 2
CompareRegistry entry

3 tools: 2 change things and 1 only read.

Scanned Oct 22, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http security-checks https://atkvn.com/agent/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warncheck_post_quantum_tls

    The server marks "check_post_quantum_tls" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_post_quantum_tls" says "post": a word for a change.

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 2Claude Code: ask
  • check_post_quantum_tlsDoes this public hostname negotiate hybrid post-quantum key exchange (X25519MLKEM768)?Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "check_post_quantum_tls" says "post": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "check_post_quantum_tls" says "post": it sends or publishes something to other people.

    Findings

    • Warn

      The server marks "check_post_quantum_tls" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_post_quantum_tls" says "post": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Does this public hostname negotiate hybrid post-quantum key exchange (X25519MLKEM768)? Returns TLS version, hybrid yes/no and a one-line verdict. Free. One TLS handshake per probe, no scanning.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • check_tls_certificateCertificate issuer, expiry date, days left, and whether the chain verifies for the hostname from a strict client (catches missing intermediate certificates and name mismatches).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Certificate issuer, expiry date, days left, and whether the chain verifies for the hostname from a strict client (catches missing intermediate certificates and name mismatches). Free.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
Only reads 1Claude Code: allow
  • audit_wazuh_rulesFinds Wazuh custom rules that pass wazuh-analysisd -t but are dropped at load (load order across ruleset/rules and etc/rules, missing parents, duplicate or colliding ids).Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • private-dataThe input names a file (input.files), and the tool reads: it reads files.
    Description, as the server wrote it
    Finds Wazuh custom rules that pass wazuh-analysisd -t but are dropped at load (load order across ruleset/rules and etc/rules, missing parents, duplicate or colliding ids). Input: list of {filename, xml}. Supported versions: 4.14.7, 4.14.9. Free: counts + 2 findings. Full report: pass api_key.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

2 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__security-checks__check_post_quantum_tls"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http security-checks https://atkvn.com/agent/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__security-checks__audit_wazuh_rules"
    ],
    "ask": [
      "mcp__security-checks__check_post_quantum_tls",
      "mcp__security-checks__check_tls_certificate"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as security-checks. Review it before you use it.

Capability tags behind 3 rules
  • mcp__security-checks__check_post_quantum_tls untrusted-input, outbound
  • mcp__security-checks__check_tls_certificate untrusted-input
  • mcp__security-checks__audit_wazuh_rules private-data