Contractbook

Security checks across malware telemetry and agentic risk

Overview

This Contractbook skill is a plausible integration, but it gives an agent broad authenticated access to sensitive contract data and raw write/delete API capability without clear confirmation safeguards.

Install only if you trust Membrane with the relevant Contractbook workspace. Use a least-privileged account, prefer built-in Membrane actions over raw proxy requests, manually confirm any write/delete/billing/GDPR/workflow action, 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: 90% confidence
Finding: The skill explicitly instructs agents to use a generic proxy capable of GET, POST, PUT, PATCH, and DELETE against the Contractbook API, but it does not require confirmation or warn about the consequences of state-changing operations. In an agent setting, this increases the risk of accidental modification or deletion of contracts, metadata, or compliance-related records based on ambiguous prompts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal