Security audit

Slack 消息 LITE

Security checks across malware telemetry and agentic risk

Overview

This skill transparently provides basic Slack message sending and channel-history reading, with expected privacy and posting risks but no hidden or malicious behavior found.

Install only where the Slack bot is authorized for the relevant workspace and channels. Before using it, confirm the destination and message content, keep read limits small, and avoid retrieving or reposting sensitive Slack history unless you have permission.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill explicitly supports reading Slack channel history but does not warn users that retrieved messages may contain private, confidential, or regulated data. In an agent context, this omission can lead users to invoke message-history reads without realizing the privacy and data-handling implications, increasing the chance of unintended exposure in prompts, logs, or downstream tool use.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill enables sending messages to Slack channels or users but does not clearly warn that this creates external side effects and may contact unintended recipients. In an agent-driven workflow, missing consent and destination-validation guidance can cause accidental notifications, misinformation, or disclosure of internal data to the wrong channel or person.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.