ClawHub
Back to skill

Security audit

FullEnrich

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-focused FullEnrich connector wrapper that uses the OOMOL oo CLI and does not show hidden, destructive, or exfiltrating behavior.

Install this only if you intend to use OOMOL's oo CLI with a connected FullEnrich account. Expect read-only lookups and credit-balance checks to go through OOMOL/FullEnrich and potentially consume FullEnrich credits; review any future action tagged write or destructive before approving it.

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 overly broad because it directs the agent to use this skill for ANY FullEnrich-related request, without narrowing by task type, risk, or necessity. This can cause unnecessary routing to an external connector and reduce opportunities for safer alternatives or per-task review, especially if future actions include writes or higher-risk operations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.