Signus Signature Generator

• Outcome: Review
• Latest audit: May 29, 2026 at 9:25 PM UTC
• Version:
  1.0.2

Overview

The skill mostly does what it claims, but its file-writing boundary is weaker than disclosed and should be reviewed before use.

Install only if you are comfortable sending the requested signature name or initials to Signus and storing generated files locally. The maintainer should add path containment checks, stronger filename sanitization, ZIP entry validation, size limits, and an explicit third-party data-sharing notice before broad use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 86% confidence
• Finding: The skill explicitly instructs execution of a Node.js script that performs outbound requests to a remote API, yet no permissions are declared. That mismatch is a real security governance issue because it hides network capability from reviewers and policy enforcement, making data egress and external dependency use less visible and less controllable.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The script transmits user-supplied identity data such as name, firstName, lastName, or initials to an external Signus API without any built-in notice, consent check, or minimization. In an agent skill context this is a real privacy/security issue because personally identifying information is exfiltrated off-platform to a third party, and users may not realize that requesting a signature image causes their identity data to be sent externally.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill writes remote content returned by the Signus service directly to the local filesystem and then extracts ZIP content into a user-accessible media directory, without validation of the archive contents or any user warning. This is dangerous because untrusted remote files can persist locally, consume disk space, or, if the ZIP library permits path traversal or symlink abuse, overwrite files outside the intended directory.

VirusTotal

66/66 vendors flagged this skill as clean.