ClawHub
Back to skill

Security audit

Axiom

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Axiom connector wrapper that can read, create, and delete Axiom datasets, with explicit confirmation rules for state-changing actions.

Install only if you are comfortable letting the OOMOL connector operate your Axiom account. Review dataset deletion requests carefully, because the skill supports destructive Axiom actions when explicitly approved.

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
93% confidence
Finding
The trigger text is extremely broad: it directs the agent to use this skill for ANY Axiom request, including reads, writes, and deletions. That increases the chance of unintended invocation and can route loosely related user requests into a powerful integration capable of destructive actions, especially when paired with allowed Bash execution and connector actions like dataset deletion.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.