Back to skill

Security audit

Slack Member Fetch

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it fetches Slack workspace or channel member details, including sensitive directory fields, only when invoked with a Slack token.

Install only if you are authorized to use a Slack bot token with users:read, users:read.email, and conversations:read. Treat the output as sensitive employee directory data, especially exports containing emails, titles, admin/owner status, and channel membership; store it only in approved locations and avoid committing or sharing exported files.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill declares no explicit tool restrictions even though its documented behavior requires environment access, network access to Slack, and file writing. In an agent environment, missing scope declarations can allow broader-than-necessary execution or make users unaware that the skill can access tokens and export data, increasing the chance of unintended data exposure or misuse.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation encourages saving Slack member output to a file without warning that the exported data may include sensitive personal and organizational information such as names, emails, titles, admin status, and timezone. This increases the risk of privacy violations, accidental retention, insecure sharing, or downstream exfiltration of directory data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation explicitly instructs users to export Slack member data to a file, but it omits any warning that the output may contain sensitive personal data such as names, emails, and profile attributes. In the context of a Slack member enumeration skill with users:read.email scope, this increases the risk of inadvertent data leakage, insecure storage, or mishandling of employee directory information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script enumerates workspace or channel members and outputs profile attributes including email, title, timezone, admin/owner status, and account state directly to stdout or an arbitrary file. Even though this is the stated functionality, it still creates a real privacy and data-exposure risk because the skill provides bulk directory export with no consent notice, minimization, masking, scope checks, or destination restrictions, making accidental or unauthorized disclosure easier.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.