ATK Security Checks

Check PHP2Shell (CVE-2026-109618/109619)

check_php2shell

Read-onlyIdempotent

Is this PHP install exposed to PHP2Shell, the two critical unauthenticated RCE flaws patched on 21 Oct 2026 (CVE-2026-109618, CVE-2026-109619)? Paste local evidence collected on the server: php -v, php -i or php-fpm -i, cat /etc/os-release, dpkg -l 'php*' or rpm -qa 'php*'. Returns patched / vulnerable / check_vendor_backport, the exact changelog command that decides distribution builds, upgrade commands, config mitigations until patched, and a tested Wazuh rule pack for crash and OOM signals. Free. Nothing is fetched from your servers.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "evidence": "<evidence>"
    },
    "name": "check_php2shell"
  }
}

Input Schema

Name	Required	Description	Default
`evidence`	Yes	Raw output of the commands above, pasted as one text block (up to 20 KB).

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 23, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, closed-world, and non-destructive, and the description adds real context on top: no data leaves the server ('nothing is fetched'), the three possible verdicts, and the full set of artifacts returned (changelog command, upgrade commands, mitigations, Wazuh rule pack). That is the kind of behavior an agent cannot infer from hints alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The question framing is front-loaded and every sentence contributes (evidence sources, verdicts, outputs, privacy note). The middle sentence is long and packs three distinct ideas, which slightly hurts readability but wastes no content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one parameter, no output schema, and annotations covering safety, the description supplies everything else needed: input format, off-line guarantee, verdict enumeration, and return contents. An agent could call this correctly on the first try.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description goes beyond the schema's self-referential 'Raw output of the commands above' by actually enumerating the acceptable evidence sources and the `or` alternatives. Without the description the parameter would be ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact resource (a PHP install's exposure to PHP2Shell) and the two CVEs, framing it as a question the tool answers. This is clearly separable from the TLS-certificate and Wazuh-rule siblings, which target different resources entirely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete usage context by naming the exact commands whose output should be pasted (`php -v`, `php-fpm -i`, `dpkg -l 'php*'`, etc.), which tells an agent how to prepare a call. It stops short of stating when not to use it or how it relates to `audit_wazuh_rules`, despite mentioning a Wazuh rule pack.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All ATK Security Checks tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?