ClawHub
Back to skill

Security audit

STEP Parts

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it advertises: it searches step.parts and can save CAD STEP files locally, with no evidence of hidden or destructive behavior.

Install if you are comfortable with a skill that contacts step.parts and saves CAD files. Prefer a dedicated output directory, avoid --overwrite unless you mean to replace a file, and only use alternate API origins you trust.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly directs network access to external hosts and downloading STEP files to local storage, yet there is no declared permission model or user-consent boundary in the skill metadata. That mismatch can lead to unintended outbound requests and local file writes by an agent runtime that may not surface those side effects clearly to the user.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The workflow instructs the agent to download STEP files and save them locally without an explicit warning that local files will be created or modified. In an agent setting, even expected downloads are a safety issue when side effects occur without clear user awareness or confirmation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Documenting an `--overwrite` option without a prominent warning increases the risk that an agent may replace an existing local STEP file or similarly named file silently. In automated workflows, silent overwrite behavior can cause data loss, provenance confusion, or substitution of trusted CAD artifacts with newly fetched content.

Static analysis

No suspicious patterns detected.