Edusign

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This Edusign skill is coherent, but it deserves review because it gives an agent broad authenticated access to sensitive education records and account-changing API calls.

Install only if you are comfortable letting an agent use a Membrane-connected Edusign account. Use the least-privileged Edusign account available, verify or pin the Membrane CLI version, and manually approve the exact action, endpoint, HTTP method, and payload before any create, update, delete, or bulk operation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The skill advertises management of Edusign entities through named operations, but later exposes a generic proxy mechanism that can issue arbitrary authenticated API requests. That mismatch can cause an agent or user to underestimate the breadth of capability, enabling access to endpoints or data beyond the apparent curated scope and weakening safety review and permission expectations.

VirusTotal

61/61 vendors flagged this skill as clean.