ClawHub
Back to skill

Security audit

Ashby

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Ashby read/search helper that uses OOMOL's oo CLI and does not show hidden, destructive, or exfiltrating behavior.

Install only if you are comfortable letting an agent query Ashby through your OOMOL account. Review the oo CLI setup and Ashby connection before use, and require explicit confirmation before enabling or running any future actions that write, delete, or overwrite Ashby 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
85% confidence
Finding
The trigger text says to use this skill for ANY Ashby request and instead of calling the API directly, which creates an unnecessarily broad routing rule. In an agent ecosystem, this can cause over-invocation of the skill beyond narrowly intended read/search use cases, increasing the chance that the agent routes sensitive or higher-risk Ashby tasks through a skill whose scope boundaries are not clearly constrained.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.