ClawHub
Back to skill

Security audit

Slack Hub Tool Free

Security checks across malware telemetry and agentic risk

Overview

This Slack skill mostly matches its stated purpose, but its broad trigger wording and uneven disclosure of private-channel access deserve review before use.

Install only if you want an agent to send Slack messages and search Slack workspace content with your bot token. Limit the Slack app scopes to the functions you need, avoid groups:read unless private-channel access is intentional, and require explicit confirmation before sending messages or running searches.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The documentation states the free edition only provides basic send/search functionality, but later includes the `groups:read` scope for private-channel access. This mismatch can cause users or agents to grant broader Slack permissions than expected, increasing the chance of unnecessary exposure of private workspace metadata and violating least-privilege assumptions.

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
The skill initially describes channel listing as limited to public channels, but later examples and scope guidance imply access to archived and private channels. In a security-sensitive integration, inconsistent permission boundaries are dangerous because an agent may request or use broader Slack API scopes than the user reasonably expects.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger condition is broad enough to activate on generic communication or integration requests, which raises the risk that an agent will invoke Slack messaging or workspace search without sufficiently specific user intent. Because this skill can send messages and query workspace content, overbroad activation can lead to unintended data access or unintended outbound communications.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill description omits a clear warning that it can send outbound messages and search workspace data through the Slack API using a bot token. Without prominent disclosure, users may not understand that invoking the skill can transmit content externally and access organizational data, which materially affects consent and safe use.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.