Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_docker_bench

Destructive

Runs docker-bench-security checks inside an engagement-scoped cloud container with supplied argument tokens, without shell parsing, to audit Docker security.

Instructions

Run docker bench from the OpenCyber cloud container iac toolkit. The container executes docker-bench-security directly with the supplied argv tokens; shell parsing is never used. Runs from the selected engagement namespace; use relative paths for engagement artifacts.

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": {
      "engagement_id": "<engagement_id>",
      "arguments": "<arguments>"
    },
    "name": "oc_docker_bench"
  }
}

Input Schema

NameRequiredDescriptionDefault
stdinNo
argumentsYes
engagement_idYes
working_directoryNo.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotent=false. The description adds genuine behavioral detail beyond them: arguments are passed as argv tokens directly and 'shell parsing is never used,' which tells an agent how input is handled and that shell metacharacters will not be interpreted. It does not say what a destructive run affects, what permissions are needed, or how long it takes, leaving risk disclosure largely to the annotations.

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?

Two tight sentences with the execution model front-loaded and the path/scoping rule second. No filler, though the toolkit framing phrase adds little for an agent that already has the tool name.

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

Completeness1/5

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

The description fails on the two most consequential points. The annotations flag this tool as destructive, yet the description never says what a run alters or how risky it is. It also leaves the 4-parameter schema 0% documented, omitting `stdin` entirely and giving no format for `arguments`, so an agent cannot parameterize or gauge the blast radius of a Docker benchmark run.

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

Parameters3/5

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

Schema description coverage is 0% across four parameters, so the description must carry the load. It loosely maps three of them ('arguments' as argv tokens, 'engagement_id' as the selected engagement namespace, 'working_directory' via the relative-paths hint) but never documents `stdin` or explains the argument format or defaults, so the compensation is partial.

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

Purpose4/5

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

Names a specific verb and resource: it runs the `docker-bench-security` binary, and it identifies the executing context (OpenCyber cloud container iac toolkit). That makes it distinguishable from oc_kube_bench by subject matter, but the description never explicitly contrasts the two, so differentiation is implicit rather than stated.

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

Usage Guidelines3/5

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

Provides scoping context ('runs from the selected engagement namespace; use relative paths for engagement artifacts') but gives no explicit when-to-use versus when-not guidance, and does not name an alternative for non-Docker benchmarks. Usage is inferred from the tool's subject matter rather than stated.

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

Deploy Server

Other Tools