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

Penthera: Cyber Security Agent

by danoszz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Check dependencies

check_dependencies
Read-onlyIdempotent

Scan npm and Python dependencies offline from lockfiles and installed trees to flag install scripts, shell/network/eval/credential access, malicious packages, and typosquats—read-only.

Instructions

What each npm or Python dependency can do (install scripts, shell, network, eval, credential access), known-malicious packages and typosquats, read offline from the lockfile and installed tree. 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": "check_dependencies"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoProject folder to scan, relative to the workspace root or absolute inside it. Default: the workspace root.
prodNoSkip dev dependencies (npm).
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

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered structurally. The description adds genuinely new behavioral context: the scan is static and offline, sourced from the lockfile and installed tree, and it surfaces install-script/shell/network/eval/credential capabilities plus known-malicious and typosquat matches. It does not state whether results are severity-ranked or what an absent lockfile yields, though the schema's max_findings hint covers ordering partially.

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?

A single dense sentence with no filler, and the capability list is packed into parentheses efficiently. It is slightly output-first ("what each dependency can do") rather than action-first, but the scope terms "offline" and "lockfile" land early enough to orient the reader.

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

Completeness4/5

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 describing findings, and it does so via the capability categories and malicious/typosquat signals. What remains unstated is how results are structured and what a clean result looks like, but for a read-only three-parameter scanner this is close to sufficient.

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%, so path, prod, and max_findings are each documented with defaults and constraints in the schema itself. The description adds no further parameter semantics, which is acceptable given full coverage but represents no bonus value.

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 precise resource and scope: npm or Python dependencies, read from the lockfile and installed tree, reporting malicious packages and typosquats. The capability taxonomy (install scripts, shell, network, eval, credential access) makes the output substance unambiguous. It stops short of explicitly distinguishing itself from the sibling scan_repo, which also sounds like it inspects a project.

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?

"Read offline from the lockfile and installed tree" implies the usage context (static, no network, requires an existing lockfile/install) and implicitly rules out remote or URL scanning. However, there is no explicit when-to-use statement and no named alternative for cases such as live runtime analysis, which is a sibling-shaped gap left 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