ClawHub

KPI Tracker

Security checks across malware telemetry and agentic risk

Overview

This is a local KPI tracking skill that stores KPI files for its stated purpose, with no evidence of hidden execution or data sharing.

Install it only in workspaces where KPI data should be stored. Treat kpi-config.json, kpi-data.json, and saved reports as business records, and review any separate cron, Slack, Telegram, or other automation integrations before enabling scheduled delivery.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill exposes broad, generic trigger phrases like 'Give me a KPI report' and 'Which metrics are off track?' without defining clear activation boundaries, confirmation requirements, or namespace scoping. In an agent environment, this can cause unintended invocation during normal conversation and lead to unexpected reads/writes of workspace files or report generation when the user did not explicitly intend to use the skill.

Missing User Warnings

Low
Confidence
86% confidence
Finding
The skill states that it reads and writes `kpi-data.json` and may save reports under `reports/`, but it does not prominently warn users up front that using the skill modifies workspace state and creates persistent files. This can surprise users, cause accidental data persistence, and in shared or sensitive workspaces may expose business metrics or create audit/compliance issues.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal