Security audit

Local-Only 3D Printer Maintenance Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, local-only 3D-printer help skill with no implemented code paths for hardware control, persistence, credential use, or data exfiltration in the inspected artifact.

Before installing, treat any future G-code or maintenance instructions as advisory: review printer compatibility, temperatures, motion commands, and file destinations before using them. The current package appears incomplete because most action, workflow, and prompt files are empty.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The README advertises maintenance guidance and automatic G-code generation for a physical device, including hotend cleaning, calibration, and leveling, but provides no explicit warnings about hot surfaces, moving axes, firmware/printer compatibility, or the risk of hardware damage from incorrect commands. In a skill that can influence real-world printer behavior, omission of safety constraints can plausibly lead users to run unsafe procedures or generated G-code that damages the printer, print surface, or nearby surroundings.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises automatic calibration G-code generation and file export/profile features while stating that it does not control hardware, but it omits any warning that generated G-code can directly influence printer motion, temperatures, and safety-relevant behavior once used by the user. It also omits notice that saved profiles and exported logs may expose or overwrite local user data, which can mislead users into underestimating operational and privacy risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The troubleshoot command description is broad and could be activated by a wide range of unrelated user requests because it does not clearly define scope, prerequisites, or boundaries. In agent systems, underspecified triggers increase the chance of unintended workflow invocation, which can expose internal capabilities or cause actions the user did not explicitly intend.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The maintenance command is described so generically that it could match many requests involving upkeep, repair, or guidance without confirming the user actually wants this workflow. That ambiguity can lead to overbroad command routing and unintended execution of maintenance-related actions or disclosures.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manage_profiles command supports state-changing operations like save and load, but its description does not constrain when each action should be triggered or what profile scope is allowed. Broad activation for commands that modify or retrieve stored profiles increases the risk of accidental state changes, unauthorized overwrites, or loading the wrong configuration.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The export_logs description is generic and lacks boundaries around which logs may be exported, by whom, and under what conditions. Even if the workflow is benign, vague triggering for data export features can lead to unintended disclosure of operational or maintenance information.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.