ClawHub
Back to skill

Security audit

Slack

Security checks across malware telemetry and agentic risk

Overview

This skill gives an agent Slack read and write abilities through an OOMOL connector, but the behavior is disclosed, Slack-scoped, and includes confirmation requirements for state-changing actions.

Install this only if you want the agent to operate Slack through your OOMOL-connected account. Review requested write, upload, update, schedule, and delete actions carefully before approving them, and treat read/search results as potentially sensitive workspace data.

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
94% confidence
Finding
The skill declares it should be used for ANY Slack request, which is an overly broad trigger that can preempt more specialized or safer handling paths. Because this skill includes both read and state-changing/destructive actions, broad automatic routing increases the chance an agent invokes high-impact Slack capabilities in contexts where narrower scoping or additional review would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.