ClawHub

Jobnimbus

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate JobNimbus integration, but it grants broad live CRM access without enough scoping or confirmation guidance.

Review before installing if your JobNimbus account contains production customer, payment, invoice, job, or account data. Use the least-privileged JobNimbus/Membrane connection available, inspect requested scopes, and require the agent to show exact changes and get explicit approval before creating, updating, deleting, invoicing, purchasing, or using raw proxy requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest description materially understates the skill's scope: it claims limited management of Organizations, Pipelines, Users, and Filters, while the body documents broad access to many CRM objects plus direct proxy API requests. This can mislead users or higher-level orchestration into invoking a much more powerful integration than expected, increasing the risk of unintended data access or modification.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The invocation text is broad enough that many ordinary requests involving JobNimbus data could trigger this skill automatically, even when the user did not intend to authorize live CRM access or mutation. In a networked integration with create/update capabilities, overbroad routing increases the chance of unintended operations against production data.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill description does not clearly warn that using the skill may send data over the network and may create or update live CRM records. Without that disclosure, users may reasonably interpret the skill as informational, leading to privacy surprises or accidental modification of business-critical data.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal