Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_bash

Destructive

Runs arbitrary Bash scripts inside the OpenCyber container from a selected engagement directory, supporting pipelines, redirection, and asynchronous, client-cancellable execution.

Instructions

Run an arbitrary Bash script inside the OpenCyber container from the selected engagement directory. Supports pipelines and redirection; the container is the trust boundary. Execution is asynchronous and client-cancellable.

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>",
      "script": "<script>"
    },
    "name": "oc_bash"
  }
}

Input Schema

NameRequiredDescriptionDefault
stdinNo
scriptYes
environmentNo
engagement_idYes
working_directoryNo.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (destructive=true, readOnly=false, openWorld=true, non-idempotent), and the description adds genuinely new behavior: asynchronous execution, client-side cancellation, supported pipelines/redirection, and the isolation boundary. It omits how results are retrieved after an async run and what specifically can be destroyed.

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

Conciseness5/5

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

Three short, front-loaded sentences with no filler; the execution model constraint is stated before the async detail. Each sentence carries distinct information.

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

Completeness3/5

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

An output schema exists, so return values needn't be described, but the async/cancellable model leaves open how a caller obtains results or whether it blocks. For a destructive arbitrary-code-execution tool with five undocumented parameters, the description should say more about environment, stdin, and working-directory scoping.

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

Parameters2/5

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

Schema description coverage is 0% across five parameters, so the description must carry the load, but it never mentions script, stdin, environment, working_directory, or engagement_id. Only 'from the selected engagement directory' loosely hints at working_directory scoping.

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?

States a specific verb and resource ('Run an arbitrary Bash script') plus concrete scope ('inside the OpenCyber container from the selected engagement directory'), which is enough to distinguish it from the specialized oc_* tooling siblings. It stops short of explicitly framing itself as the general-purpose fallback when no dedicated tool exists.

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?

Usage is implied by 'arbitrary' and 'the container is the trust boundary', suggesting this is the escape hatch when no specialized tool fits. There is no explicit when-to-use vs. when-to-prefer-a-sibling guidance and no exclusions or prerequisites.

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