Skip to main content
Glama
Sign In
Penthera: Cyber Security Agent

Penthera: Cyber Security Agent

by danoszz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Audit AI agent config

audit_ai_tooling
Read-onlyIdempotent

Audits AI agent configurations for hidden instructions, unsafe shell commands, unpinned MCP packages, inline secrets, and wildcard permissions, then assigns an A–F grade.

Instructions

Audit the project's AI agent setup: skills, MCP servers, hooks, permissions, plugins and rule files, for hidden instructions, curl-pipe-shell, unpinned MCP packages, inline secrets and wildcard permissions. Grades A to F, or gives no grade when it finds no agent config. Offline, deterministic, read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_ai_tooling"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoProject folder to scan, relative to the workspace root or absolute inside it. Default: the workspace root.
max_findingsNoHow many findings to return, most severe first (default 50).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, so safety is covered structurally. The description still adds real value beyond them: 'offline' and 'deterministic' qualify execution in ways the hints do not, and the grading behavior (A–F, or no grade when no agent config exists) discloses output shape that no schema provides.

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?

Two sentences, front-loaded with the audited scope and followed by the outcome and execution guarantees. The enumeration of check categories is dense but each item carries selection-relevant information, so nothing is wasted.

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?

With no output schema, the description carries the burden of explaining returns and does so (A–F grade or no grade). Combined with the offline/deterministic/read-only guarantees and the explicit list of audited surfaces, an agent has everything needed to call this correctly against a two-parameter, zero-required schema.

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 100%, with both `path` and `max_findings` fully documented including defaults and bounds, so the baseline is 3. The description adds nothing further about parameter behavior — no mention of what `path` means outside the workspace or how `max_findings` interacts with severity ordering.

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

Purpose5/5

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

States a specific verb (audit) and a precisely bounded resource (the project's AI agent setup: skills, MCP servers, hooks, permissions, plugins, rule files) plus the exact failure classes it looks for. This scoping ('AI agent setup') naturally separates it from broader siblings like scan_repo or check_dependencies without needing to name them.

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 by the scope statement and the 'offline, deterministic, read-only' framing, so an agent can infer this is a safe static audit. However, there is no explicit when-to-use/when-not guidance and no pointer to a sibling such as scan_repo or explain_finding for follow-up, leaving the routing decision to inference.

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