Versioned security assessment

Report ID: SA-88A8E9A0

7/23/2026, 10:44:11 PM

freshdesk-automation security assessment v5

Skill Security Certification Report

Audit History
Scanner version 3.0.0 Audit model: codex Latest published report
Skill name
freshdesk-automation
Version
v5
Maintainer
sickn33
Source
github.com/sickn33/antigravity-awesome-skills/tree/main/skills/freshdesk-automation
Coverage
1 Files scanned · 228 Lines analyzed
Policy version
skillstore-security-audit-policy-v1

Highest confirmed finding severity

Medium

3 confirmed security findings require attention.

Installation context

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

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

The 109 command-execution alerts and three reconnaissance alerts are false positives caused by Markdown tool names and ordinary Freshdesk guidance. The external MCP endpoint is a real low-severity dependency, while third-party data access, consequential writes, and sender overrides require safeguards.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

Audit attestation

Active attestation

A public attestation is available for this exact report.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 228 Lines analyzed

4 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

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  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 50 evidence locations

Capability review items (1)
Low
SKILL.md:21
Hardcoded URL
**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API k
Line 21 directs users to configure the external Rube MCP endpoint. This is an intentional third-party network and trust dependency, although it is not evidence of malware.

Risk findings

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

Confirmed security concerns (3)

RISK-001 Medium
SKILL.md:11SKILL.md:21-25
Third-Party MCP Handles Freshdesk Data
The skill routes support workflows through Rube MCP and asks users to authenticate Freshdesk through its returned link. The intermediary can access sensitive records and writes.
The source explicitly requires an external Rube MCP endpoint and a Freshdesk connection. The documented workflows include reading and changing customer support data.
RISK-002 Medium
SKILL.md:37-38SKILL.md:99-101SKILL.md:129-135
Consequential Actions Lack Explicit Confirmation Gates
The workflows permit ticket writes, public replies, bulk contact imports, and company changes without a final preview or confirmation. Ambiguous requests could alter records or contact customers.
The listed sequences directly invoke mutating and externally visible tools. No cited workflow requires presenting the final scope and obtaining confirmation before execution.
RISK-003 Medium
SKILL.md:109-110
Agent Identity Overrides Lack Authorization Guidance
Reply parameters can override the sender address or act on behalf of another agent. The skill does not require authorization checks before using these identity controls.
The source explicitly documents sender and agent overrides. Freshdesk may enforce permissions, but the skill provides no guidance to verify delegated authority.

Remediation

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

  1. FIX-001
    Medium
    Rube MCP can receive Freshdesk customer data and perform account actions.
    Disclose the intermediary, verify its privacy terms, use least-privilege Freshdesk authorization, and restrict the connection to approved accounts.
  2. FIX-002
    Medium
    Mutating workflows do not require a final confirmation.
    Preview target records, recipients, field changes, and batch size. Require explicit confirmation before writes, imports, public notes, or replies.
  3. FIX-003
    Medium
    Reply tools support sender and agent identity overrides.
    Require proof of delegated authority before setting from_email or user_id. Otherwise, use the authenticated agent identity.

Expert evidence

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

Artifact subject

Marketplace commit
88a8e9a07f4c54ab105c1c41b6267c287146b07b
Content hash
ce86179d05e431603a60ba9ae941ec99eb9fea73fee5227fa20874c0914fc3c2
Tree hash
078c4af382112c534b30f76afb06454cc14367bcac33e520e12821c6822f7a9a
Skill path
skills/sickn33/freshdesk-automation
Audit payload hash
aa8974a2a3510215837f0f1df2217759

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

JSON report Signed attestation CITATION.cff SARIF 2.1.0 Signed installation manifest Source

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

Audit attestation: active