Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_ropgadget

Destructive

Run ROPgadget on binaries within an engagement namespace to find ROP gadgets, using direct argv execution without shell parsing.

Instructions

Run ropgadget from the OpenCyber binary toolkit. The container executes ROPgadget 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_ropgadget"
  }
}

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

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is carried structurally. The description adds genuinely useful behavior: the binary is exec'd directly with argv tokens and no shell parsing occurs, and execution is scoped to the selected engagement namespace with relative working paths. It does not explain why the call is flagged destructive, what state could be altered, or any timeout/output-size limits.

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?

Three short sentences, front-loaded with the action, then mechanism, then execution context. No filler or repetition, though the middle sentence's semicolon clause is slightly expository for what it conveys.

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?

The output schema exists, so return values need no prose. What an agent must know to call this correctly, namely that arguments are passed as discrete argv tokens without shell interpretation and that paths resolve relative to the engagement namespace, is present. The residual stdin gap is minor for a gadget-listing tool.

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 is the only prose source. It illuminates three of four parameters indirectly: 'supplied argv tokens' maps to arguments, 'selected engagement namespace' maps to engagement_id, and 'use relative paths' maps to working_directory. The stdin parameter is never mentioned, so the description only partially compensates for the complete lack of schema documentation.

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?

The description names a specific verb (run) and a specific resource (the ROPgadget binary within the OpenCyber toolkit), and states the execution mechanism (argv tokens, no shell). It is distinguishable from siblings by naming the wrapped binary, but it never states what ROPgadget actually produces (gadget offsets in a binary), leaving the analytical purpose to be inferred from the tool name alone.

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 guidance on when to choose this over oc_bash (which could run the same binary) or oc_angr_analyze, and no stated preconditions such as a target file existing in the engagement namespace. The only guidance given is operational ('use relative paths for engagement artifacts'), not selection guidance.

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