Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_trivy

Destructive

Runs Trivy scans inside a selected engagement namespace to detect vulnerabilities and IaC misconfigurations via direct argv execution without shell parsing.

Instructions

Run trivy from the OpenCyber cloud container iac toolkit. The container executes trivy 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_trivy"
  }
}

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

A3.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely new behavioral context: argv tokens are passed directly and shell parsing is never used (so shell metacharacters/pipelines won't work), and execution is scoped to the engagement namespace with relative artifact paths.

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 what the tool runs and immediately followed by the two constraints an agent most needs (no shell parsing, relative paths). No filler; only the missing stdin detail keeps it from being exhaustive.

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 need not be described, and annotations cover the destructive/open-world profile. However, for a four-parameter wrapper with zero schema descriptions, the definition should still say what stdin is for and clarify working_directory behavior; it currently leaves those to inference.

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?

With 0% schema description coverage the description must carry the parameter burden, and it only partly does: "arguments" is explained as argv tokens (clarifying quoting/escaping expectations) and "engagement_id"/"working_directory" are implied by the namespace and relative-path sentences. The "stdin" parameter is never mentioned, leaving one of four parameters undocumented.

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 gives a specific verb and resource ("Run trivy from the OpenCyber cloud container iac toolkit") and names the execution model, so an agent knows exactly what is invoked. It does not distinguish this from sibling wrappers (e.g. other oc_* binary wrappers) beyond the tool name itself.

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 context is implied rather than stated: running from the selected engagement namespace and using relative paths for engagement artifacts tells the agent how to invoke it in this environment. There is no explicit when-to-use/when-not-to-use guidance or routing to alternatives such as a generic shell or other IaC scanners.

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