Halo Cli Moderation Notifications

• Outcome: Review
• Latest audit: May 29, 2026 at 9:28 PM UTC
• Version:
  0.1.1

Overview

The skill matches Halo moderation work, but it gives an agent commands for irreversible moderation changes without enough confirmation or visibility guidance.

Install only if you want an agent helping with Halo moderation. Before allowing mutations, confirm the active Halo profile, site, exact resource ID, and whether the action is reversible; require explicit approval for deletes, approvals, hidden replies, public replies, and mark-all notification actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The skill documents destructive deletion commands using `--force` without an explicit warning that deletion is irreversible or guidance to verify the target before execution. In an automation or operator-assist context, this increases the chance of accidental deletion of comments or notifications, especially across profiles or environments.

Missing User Warnings

Medium

• Confidence: 81% confidence
• Finding: The skill shows how to create `--hidden` replies but does not explain visibility, retention, audit, or user-impact implications. In a moderation workflow, hidden replies can be misused for undisclosed internal messaging or unintentionally expose sensitive moderator content if operators misunderstand who can see the reply.

VirusTotal

66/66 vendors flagged this skill as clean.