ClawHub
Back to skill

Security audit

Agent Lens

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local observability guide for tracking LLM API usage and costs, with its install and local data storage behavior disclosed.

Before installing, confirm you want a third-party GitHub package to record local LLM API telemetry. Review what data your integration records, especially if prompts or usage metadata are sensitive, and periodically clean the local database if you do not want long-term history retained.

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
86% confidence
Finding
The activation cues are broad cost- and billing-related phrases that can match many ordinary user requests, increasing the chance the skill is invoked outside a narrowly intended observability context. Because this skill can steer the agent toward installing or using a third-party monitoring package and operational commands, unintended activation could cause unnecessary tool use, user confusion, or exposure to locally stored telemetry paths and workflow assumptions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.