ClawHub

Nabla

Security checks across malware telemetry and agentic risk

Overview

This Nabla skill is coherent, but it gives an agent broad authenticated access to sensitive mental-health data without enough built-in safeguards.

Install only if you trust Membrane, the skill publisher, and your agent with the connected Nabla account. Use the least-privileged account available, prefer pre-built Membrane actions, avoid unnecessary PHI retrieval, require explicit confirmation before creating, editing, exporting, or deleting records, and revoke the connection when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough to trigger on many user requests involving 'data', 'records', or 'workflows', which can cause the agent to invoke this skill outside a narrowly intended Nabla context. Because Nabla handles highly sensitive mental-health data, overbroad routing increases the chance of unnecessary exposure, inappropriate actions, or privacy-impacting reads/writes.

Missing User Warnings

High
Confidence
94% confidence
Finding
The documentation explicitly enables direct proxy requests and general data operations against a mental-health platform without requiring safeguards, user confirmation, least-privilege guidance, or warnings about regulated/sensitive health information. In this context, unrestricted read/write guidance can lead to privacy violations, unauthorized modification of clinical records, or unsafe automation affecting patients and providers.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal