ClawHub
Back to skill

Security audit

Slack

Security checks across malware telemetry and agentic risk

Overview

This Slack skill is a disclosed connector wrapper that can read, post, update, and delete Slack content through the user's connected OOMOL account, with confirmation instructions for write and destructive actions.

Install only if you are comfortable letting the agent operate Slack through your connected OOMOL account. Review payloads before approving posts, updates, reactions, uploads, scheduled messages, or deletes, and be aware that read actions can expose Slack messages, files, channels, and user metadata visible to that account.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description instructs the agent to use this skill for ANY Slack-related request, which is broader than necessary and can override safer, more context-specific handling. In an agentic environment, this kind of blanket routing increases the chance of invoking high-privilege Slack read/write/destructive actions unnecessarily or without sufficient per-task scrutiny.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.