Slack

Security checks across malware telemetry and agentic risk

Overview

This Slack skill is a coherent connector wrapper that discloses its read, write, and delete capabilities and requires user confirmation for state-changing actions.

Install this only if you are comfortable giving an OOMOL-connected Slack bot access to the Slack data and actions your workspace grants it. Review requested Slack scopes during connection, and require explicit approval before the agent posts, updates, schedules, or deletes messages.

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: 95% confidence
Finding: The skill description directs agents to use this skill for any Slack-related task, which can override more specific tooling choices and encourage unnecessary access to broad Slack capabilities. In an agentic environment, overly broad routing increases the chance of acting on Slack data or mutating Slack state when a narrower, safer path would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal