ClawHub
Back to skill

Security audit

Slack工作区管家LITE

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Slack helper that uses ClawLink OAuth to list workspace data and send channel messages, with no hidden scripts or unrelated behavior found.

Before installing, confirm you trust ClawLink with the Slack workspace connection, review the Slack OAuth scopes, and use this only where the agent is allowed to list workspace users/channels and post messages. Avoid using untrusted callback URLs and check channel IDs and message text before posting.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to send Slack messages to a live workspace but does not clearly warn that this is an external write action with real-world effects. In an agent setting, missing disclosure and confirmation guidance can cause unintended outbound messages, spam, or disclosure of sensitive content into production channels.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Documenting a callback_url parameter without warning that results may be posted to a third-party endpoint creates a data-exfiltration risk. Users or downstream agents may supply an attacker-controlled URL, causing Slack-derived data or workflow outputs to be transmitted outside the trusted environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.