Versioned security assessment

Report ID: SA-1200D2F8

7/8/2026, 5:12:24 AM

azure-validate security assessment v4

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
azure-validate
Version
v4
Maintainer
microsoft
Source
github.com/microsoft/github-copilot-for-azure/tree/main/plugin/skills/azure-validate/
Coverage
18 Files scanned · 1,301 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

High

2 confirmed security findings require 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.

The static findings were reviewed in context. Most scanner hits are Markdown examples, relative documentation links, or project plan references rather than executable attacks. SKILL.md still contains authority-style prompt language and a mandatory deployment handoff, which create semantic marketplace risk.

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

18 Files scanned · 1,301 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 2 evidence locations

Filesystem access

May read or write local files.

Observed in 8 evidence locations

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 24 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 High
SKILL.md:12SKILL.md:52-59
Prompt Injection Attempt Detected
The file says "AUTHORITATIVE GUIDANCE" and "officially verified way to set plan status to `Validated`." These authority claims can pressure an agent to trust the skill over marketplace or host policy.
The file uses authority language and verification claims that match prompt-injection indicators. The surrounding text directly instructs agent behavior.
RISK-002 High
SKILL.md:63-65references/recipes/azd/README.md:164-166references/recipes/terraform/README.md:144-146
Unexpected Deployment Handoff
The file says "After ALL validations pass, you MUST invoke azure-deploy." A validation tool should not mandate a deployment transition without explicit user approval.
Multiple files state that successful validation leads to azure-deploy. This is a clear workflow escalation beyond validation.

Remediation

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

  1. FIX-001
    High
    Authority-style prompt language
    Remove claims such as authoritative guidance and officially verified. State that all instructions remain subject to host safety policies and user approval.
  2. FIX-002
    High
    Mandatory deployment handoff
    Change the azure-deploy step into an optional recommendation. Require explicit user confirmation before any deployment workflow starts.
  3. FIX-003
    Medium
    Command examples need clearer safety boundaries
    Label commands that modify local files, azd environment values, or Azure state. Tell agents to explain effects before running them.

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