ClawHub
Back to skill

Security audit

roundtable-forum

Security checks across malware telemetry and agentic risk

Overview

This skill is a local roundtable discussion aid, with documentation gaps around reminders and saved outputs but no evidence of hidden execution, exfiltration, destructive behavior, or credential use.

Reasonable to install as a local discussion helper. Before enabling any reminder, confirm exactly what Cron entry will be added and how to remove it. Avoid discussing sensitive information if you plan to save knowledge-network outputs, and review any missing helper files separately if they are later added.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README states that a daily 20:00 automatic reminder is configured, but it provides no details about user consent, opt-in/opt-out controls, delivery channel, or privacy implications. In an agent skill context, undocumented scheduled behavior can surprise users, create unwanted notifications, and potentially normalize background actions without explicit authorization.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The skill explicitly states that a knowledge network will be generated and written to an output file, but it does not warn users that discussion content may be persisted to disk. This can create unintended retention of sensitive prompts or personal data, especially if users discuss confidential topics and assume the interaction is ephemeral.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.