Versioned security assessment

Report ID: SA-6155FCC2

7/7/2026, 11:37:26 PM

ai-native-development security assessment v9

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
ai-native-development
Version
v9
Maintainer
AI Agent Hub
Source
github.com/ArieGoldkin/ai-agent-hub/tree/main/skills/ai-native-development
Coverage
10 Files scanned · 4,519 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 findings are false positives from TypeScript template literals, markdown examples, local links, and environment variable configuration. One real issue remains: the agentic workflows reference uses eval() on calculator input, which can execute arbitrary JavaScript. I also flagged the agent template because it demonstrates side-effecting tools without an approval gate.

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

10 Files scanned · 4,519 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.

Observed in 1 evidence location

Network access

May connect to external services.

Observed in 10 evidence locations

Filesystem access

May read or write local files.

Observed in 2 evidence locations

Env variables

May read values from the process environment.

Observed in 11 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 109 evidence locations

Capability review items (1)
High
references/agentic-workflows.md:88
Dynamic code evaluation with eval()
return { result: eval(expression) }
The reference calculator calls eval(expression) on tool input, which could execute arbitrary JavaScript if copied into an application. This is a real code execution risk despite being documentation.

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
templates/agent-workflow-template.ts:42-70templates/agent-workflow-template.ts:111-116templates/agent-workflow-template.ts:132-190
Autonomous Side-Effecting Tool Use Without Approval Gate
The agent template lets model output select tools such as query_database and send_email during a ReAct loop. Applications copied from this template should add authorization, allowlists, and human approval for side effects.
The template explicitly defines database and email tools and invokes selected tools from model output. The implementations are stubs, so the impact depends on how users adapt the template.

Remediation

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

  1. FIX-001
    High
    Unsafe eval calculator example
    Replace eval with a safe math parser or a strict expression evaluator with an allowlist.
  2. FIX-002
    Medium
    Autonomous agent tools can cause side effects
    Add approval checks, role-based authorization, and tool-specific validation before database or email actions.
  3. FIX-003
    Low
    Example environment variables need secret-handling guidance
    State that API keys must stay in server-side environment storage and must never appear in prompts or client bundles.

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

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

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

Audit attestation: not_attestable