Discord AI Dispatcher

• Outcome: Review
• Latest audit: May 29, 2026 at 9:30 PM UTC
• Version:
  1.7.8

Overview

This appears to be a legitimate Discord/webhook notification guide, but it needs review because its recovery workflow can automatically reset local state and force-send or update external notifications.

Review before installing or following this skill. Use dedicated low-privilege webhooks, protect local config files, back up state before resets, require manual approval and a dry-run preview before Heal Mode or backlog replays, cap resend volume, and make scheduled tasks easy to audit and disable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The README describes a broadly applicable 'dispatcher' skill with no explicit trigger boundaries, authorization constraints, or safe operating scope. In an agent context, this can enable overbroad invocation for message routing, state repair, webhook dispatch, and backlog replay, increasing the chance that the capability is used in unintended contexts or against unintended data sources.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The guidance explicitly recommends deleting a corrupted state file and re-initializing automatically, but it does not require backup, operator confirmation, or warning about potential loss of local state and replay/duplication side effects. In an automation skill that controls notification delivery state, destructive self-healing can erase auditability and cause missed, repeated, or inconsistent downstream actions.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill says the agent should automatically suggest or implement state realignment and force-inject missed notifications, including bypassing deduplication in heal mode, without requiring explicit approval or guardrails. In this context, those actions modify local state and external systems, creating a real risk of duplicate sends, replay of stale events, integrity loss in notification history, and unintended operational impact.

VirusTotal

65/65 vendors flagged this skill as clean.