Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_binwalk

Destructive

Execute binwalk on engagement artifacts to identify embedded files, firmware components, and binary structures using direct argv input with no shell parsing.

Instructions

Run binwalk from the OpenCyber binary toolkit. The container executes binwalk 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_binwalk"
  }
}

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

B3.3/5.0
Behavior3/5

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

The description usefully discloses execution mechanics beyond the annotations: argv tokens are passed directly with no shell parsing, and the process runs inside the selected engagement namespace. However, it never explains the destructiveHint=true semantics — that binwalk typically writes extracted files to disk — nor where that output lands, which is the key behavioral risk for a file-writing tool.

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 sentences, front-loaded with what the tool is, followed by execution semantics and path constraints. Every sentence carries distinct information with no filler.

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?

The presence of an output schema removes the need to describe return values, and the execution model is covered. But for a destructive tool with zero schema-level parameter documentation, the gaps around stdin, extracted-file behavior, and working-directory semantics leave an agent guessing on the risky parts.

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%, so the description must carry the full burden. It clarifies the two most important parameters (arguments = raw argv tokens without shell parsing, working_directory implied by the engagement namespace and relative-path rule), but leaves stdin and engagement_id unaddressed and gives no format hints for argv composition.

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 binwalk from the OpenCyber binary toolkit," so an agent knows exactly which binary is invoked. It does not distinguish this from a general-purpose sibling such as oc_bash, which could also run binwalk, so sibling differentiation is absent.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance and no named alternative. The only operational steering is "use relative paths for engagement artifacts," which is a path convention rather than usage guidance for selecting this tool over oc_bash.

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