ClawHub
Back to skill

Security audit

Document360

Security checks across malware telemetry and agentic risk

Overview

This is a narrowly scoped Document360 helper that uses the OOMOL CLI to read/search connected knowledge base data, with no artifact-backed evidence of hidden or destructive behavior.

Install only if you are comfortable connecting Document360 through OOMOL and having Document360 queries run via the oo connector. Treat it as suitable for listing and searching knowledge base content, and confirm explicitly before using any connector action that would change or delete data.

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
87% confidence
Finding
The trigger text is unusually broad: it directs use of this skill for ANY Document360 request and instead of calling the API directly. In an agentic environment, such broad routing can cause unintended invocation on loosely related requests, increasing the chance of unnecessary external data access or connector use without sufficiently precise intent matching.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.