ClawHub
Back to skill

Security audit

Personal AI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Personal AI connector wrapper that can read and write Personal AI data, with user confirmation required for state-changing actions.

Install only if you intend to let the agent use your OOMOL-connected Personal AI account. Review any proposed write payload carefully before approval, especially uploads to memory or document libraries, because those actions can persist information in your Personal AI account.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest description says to use this skill for "ANY Personal AI request" and "instead of calling the API directly," which is an overly broad trigger that can cause the agent to invoke the skill in situations where more constrained or safer handling would be appropriate. Broad invocation criteria increase the attack surface for unintended writes, schema-driven command construction, and execution of setup steps involving external tooling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.