Structurizr

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal Structurizr integration skill, with some caution needed because it can make authenticated remote API changes.

Install only if you want an agent to access Structurizr through Membrane. Confirm the target connection and workspace before use, prefer curated Membrane actions for routine tasks, and require explicit approval before any POST, PUT, PATCH, or DELETE request that could change or delete Structurizr data.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The description is broad enough to route this skill for generic 'manage data' or 'automate workflows' requests, even when the user did not explicitly ask to use Structurizr. Because the skill enables authenticated network actions against a remote service, over-broad invocation increases the chance of unintended external reads or writes.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill documents arbitrary proxied API requests, including mutating methods like POST, PUT, PATCH, and DELETE, without an explicit warning or confirmation requirement for remote state changes. In an agent setting, this can normalize direct modification of Structurizr data and increase the risk of accidental destructive actions against authenticated resources.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal