Security audit

Slack (Socket Mode)

Security checks for vulnerabilities and agentic risk

Overview

This Slack skill is mostly coherent, but it enables deleting, editing, pinning, sending, reading, and profile lookups in Slack without clear safety limits or confirmation guidance.

Install only if you are comfortable giving the agent Slack authority through the configured bot token. Limit the token to the smallest needed Slack scopes and channels, and manually confirm any delete, edit, pin, unpin, DM, or member profile lookup before allowing the agent to act.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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: 95% confidence
Finding: The skill explicitly enables destructive operations such as delete, edit, pin, and unpin, but provides no guidance to require user confirmation, scope checks, or audit awareness before performing them. In an agentic setting, this increases the chance of unintended or socially engineered destructive actions against Slack content, especially because the instructions present these actions as routine defaults.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill advertises member-info retrieval returning email, real name, avatar URLs, timezone, and status data without any privacy, authorization, or purpose-limitation warning. This normalizes collection of personally identifiable and profile data and could enable unnecessary disclosure or misuse if the agent is prompted to enumerate or inspect users without a legitimate need.

Static analysis

No suspicious patterns detected.