Signaturit

Security checks across malware telemetry and agentic risk

Overview

This Signaturit skill is coherent, but it needs review because it gives an agent broad authenticated access to change sensitive business, document, user, and role data without clear approval guardrails.

Install only if you trust Membrane and the agent with the selected Signaturit account. Use the least-privilege account available, verify the connection ID and target workspace, require explicit approval before any POST, PUT, PATCH, DELETE, user, role, organization, file, template, or signature change, and revoke the Membrane connection when finished.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly documents a generic proxy mechanism that supports destructive HTTP methods like POST, PUT, PATCH, and DELETE without any warning, confirmation requirement, or guardrails around data-changing operations. In an agent setting, this can enable unintended or overly broad writes directly against the Signaturit API, increasing the risk of accidental modification, deletion, or misuse of sensitive signing workflows and records.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal