ClawHub
Back to skill

Security audit

Fulcra Onboarding

Security checks across malware telemetry and agentic risk

Overview

This onboarding skill is a disclosed setup and capability guide for Fulcra, but users should understand it connects agents to sensitive personal data and a remote file store.

Install only if you want an agent to help connect to Fulcra and potentially work with personal context, health/location/calendar-derived data, agent logs, and remote files. Approve authentication, installs, uploads, downloads, and data changes only when you understand the specific data and destination involved.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (4)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The file is presented as onboarding/setup guidance, but it authorizes far broader capabilities: querying sensitive life data, creating schemas, and managing remote files. This scope expansion can cause agents or users to treat the skill as a general-purpose operational interface, increasing the chance of unnecessary access to private data and unintended actions beyond initial setup.

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
Including upload, download, listing, and versioned remote file management in an onboarding skill grants powerful data movement capabilities that are unrelated to initial setup. In the Fulcra context, where stored content may include sensitive personal and agent-generated data, this broadens the attack surface for exfiltration, overwrite, or unauthorized persistence.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documents remote upload/download behavior without a clear user-facing warning that files and metadata may be transmitted to and stored in a remote service. Because Fulcra is described as collecting sensitive life, activity, and agent data, omission of an explicit privacy notice can lead to accidental disclosure or retention of personal information.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The documentation states that credentials will be persisted locally but does not frame this as a user-facing security consideration or provide guidance on protecting the token file. Users or agents may unknowingly leave long-lived credentials on shared systems, increasing exposure if the host is compromised or multi-user.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.