Versioned security assessment

Report ID: SA-3E4B6C31

7/9/2026, 9:13:15 AM

helpdesk-automation security assessment v6

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
helpdesk-automation
Version
v6
Maintainer
sickn33
Coverage
1 Files scanned · 176 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

1 confirmed security finding requires attention.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Most static external-command alerts are false positives caused by Markdown backticks around tool names, parameters, and fenced examples. The hardcoded Rube MCP URL is a real low severity network dependency, and the skill routes support data through a third-party MCP integration. No prompt injection or malicious command execution evidence was found.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 176 Lines analyzed

2 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 1 evidence location

Filesystem access

May read or write local files.

Not recorded by this audit

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 28 evidence locations

Capability review items (1)
Low
Hardcoded URL
**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API k
Line 21 instructs users to add https://rube.app/mcp as an MCP server, creating a real third-party network dependency. The endpoint appears intended for setup, but it affects HelpDesk authentication and data access.

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (1)

RISK-001 Medium
Third-Party MCP Access to HelpDesk Data
The skill instructs users to add Rube MCP, authenticate HelpDesk, and list tickets, views, canned responses, and custom fields. This creates a third-party data access path for support information.
The setup and workflow lines directly describe the external MCP endpoint, authentication, and read-only HelpDesk data tools. No malicious exfiltration was found, but the third-party data handling risk is clear.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    Medium
    Rube MCP receives access to HelpDesk data.
    Tell users to approve Composio Rube access only for trusted accounts and permitted support data.
  2. FIX-002
    Low
    Markdown formatting triggers external command alerts.
    Add a manifest note that the skill contains documentation only and does not execute local shell or Ruby commands.
  3. FIX-003
    Low
    Authentication happens through an external MCP setup flow.
    Tell users to verify the rube.app domain and requested HelpDesk authorization scope before completing authentication.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
Unavailable
Content hash
Unavailable
Tree hash
Unavailable
Skill path
Unavailable
Audit payload hash
Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Verify and export

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable