ClawHub
Back to skill

Security audit

Faraday

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Faraday connector helper that uses the OOMOL oo CLI for read-only Faraday account data access.

Install this only if you intend to let your agent read Faraday account, dataset, target, trait, scope, and usage information through your OOMOL-connected account. Review the oo CLI installer before running it, and keep write or destructive connector actions subject to explicit confirmation if future versions add them.

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
88% confidence
Finding
The instruction to use this skill for ANY Faraday request is overly broad and can cause the agent to invoke the skill whenever Faraday is merely mentioned, even if the user's intent is unrelated or better served another way. In an agentic system, this can create unintended tool use, unnecessary data access, and expanded exposure of connected account data without sufficiently narrowing activation conditions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.