ClawHub

Plausible

Security checks across malware telemetry and agentic risk

Overview

This Plausible Analytics skill is transparent and purpose-aligned, with bounded local memory and a declared API key requirement.

Install only if you are comfortable letting the agent query your Plausible analytics with PLAUSIBLE_API_KEY. Use a scoped Plausible key where possible, and review or delete ~/plausible/memory.md if you do not want tracked domains, goals/events, preferences, or cached query context retained locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs creating and maintaining a persistent memory file under the user's home directory, but provides no notice, consent flow, retention guidance, or limits on what may be stored. In an analytics context, that memory can accumulate domains, goals, usage patterns, and preference data over time, creating privacy and persistence risks if the user is unaware or if the file is accessed by other tools or users on the system.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to persist user-specific analytics configuration, including tracked site IDs, base URL, defaults, and event/goals, into a local file without any disclosure, consent, retention limits, or access controls. While this is not a secret like an API key, it is still sensitive operational metadata that can reveal internal domains, self-hosted infrastructure, and business KPIs, and local persistence increases exposure to unintended reuse or disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal