ClawHub
Back to skill

Security audit

Fixer

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Fixer exchange-rate connector using the OOMOL CLI, with no hidden, destructive, or unrelated behavior found.

Install only if you intend to use OOMOL's `oo` CLI with a connected Fixer account. Be aware that the skill may route Fixer-related requests through OOMOL, and only run the one-time installer or login steps when you actually need to set up or repair the CLI connection.

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 skill description says to use this skill for ANY Fixer request, which is an overly broad routing rule that can cause the agent to invoke the skill whenever 'Fixer' is mentioned, even if the user only wants general information or an unrelated task. In an agent system, broad activation increases the chance of unnecessary tool use, accidental external calls, and unintended disclosure of user queries to the connector path.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.