Morning Meeting Bwm

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.0

Overview

The skill matches a workplace standup automation use case, but it gives Slack conversations broad power to trigger recurring storage and cross-agent business actions without clear approval limits.

Install only after setting explicit Slack channel scopes, participant notice, retention rules, and human approval gates. Require confirmation before any task posts externally, changes financial/order data, modifies code or infrastructure, or acts on customer/support content.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (1)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill describes reading Slack conversations, extracting tasks, delegating work to other agents, executing tasks immediately, and writing summaries and task data to persistent storage, but it does not warn users about these surveillance and action-taking behaviors. This creates a transparency and consent problem: users in the channel may not realize their messages are being processed for automation, persisted, and used to trigger downstream actions.

VirusTotal

66/66 vendors flagged this skill as clean.