Schoology

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real Schoology integration, but it gives an agent broad access to sensitive school data and write-capable API requests without clear safety gates.

Install only if you trust Membrane and intend to connect Schoology. Use a least-privileged Schoology account where possible, review granted permissions, and require explicit user confirmation before changing or exporting grades, attendance, users, roles, settings, imports, exports, or other administrative records.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The invocation description is overly broad: 'Manage data, records, and automate workflows' can match many Schoology-related requests without clearly constraining scope or operation type. In an agentic setting, this increases the chance the skill is selected for sensitive educational records tasks, including student data access or modification, without an explicit user intent check.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill instructs the agent to run actions and proxy raw API requests against Schoology without requiring safety gates for read vs. write operations, privacy review, or user confirmation. Because Schoology commonly contains sensitive student, parent, and staff data, this can lead to unauthorized disclosure, bulk export, or destructive changes if the agent misinterprets a request or is prompt-injected.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal