Versioned security assessment

Report ID: SA-12E52FED

6/30/2026, 7:57:29 AM

azure-ai security assessment v2

Skill Security Certification Report

Audit History

Audit model: codex Historical report

Skill name: azure-ai
Version: v2
Maintainer: microsoft
Source: github.com/microsoft/github-copilot-for-azure/tree/main/plugin/skills/azure-ai/
Coverage: 15 Files scanned · 519 Lines analyzed
Policy version: Unavailable

Confirmed finding summary

No confirmed security findings

The completed audit recorded no confirmed security findings. This is not proof that the Skill has no side effects.

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.

Static analysis reported 195 potential issues, including a critical combined-risk heuristic. Manual review found documentation-only Markdown, SDK examples, and official Microsoft Learn links with no executable scripts, exfiltration behavior, or prompt injection.

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

15 Files scanned · 519 Lines analyzed

0 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.

Source

Binding unavailable
Artifact

Identity incomplete
Audit

Complete
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.

Observed in 2 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 4 evidence locations

Risk findings

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

No confirmed security findings were recorded for this completed audit.

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.

Static false positives ignored (5)

Low

SKILL.md:12-30 references/sdk/azure-ai-contentsafety-py.md:7-15 references/sdk/azure-ai-translation-ts.md:7-15

False Positive: Markdown Code Formatting Flagged as Shell Execution

Backticks and fenced blocks describe Azure MCP commands and SDK install snippets. The files are Markdown references, not executable scripts.

The flagged text appears inside Markdown tables or fenced examples. No runtime file, script hook, or dynamic command execution path is present.

Low

references/sdk/azure-ai-transcription-py.md:15-16 references/sdk/azure-ai-translation-ts.md:14-15

False Positive: Credential Environment Variables in SDK Examples

The environment variable references show standard Azure SDK authentication examples. They do not read local secrets for hidden processing or network exfiltration.

The variables are named service endpoint and key values used directly in documented client constructors. No outbound collector or unrelated network destination appears.

Low

SKILL.md:66-67

False Positive: Official Documentation Links Flagged as Network Risk

The hardcoded URLs are direct Microsoft Learn documentation links. They are user-facing references and do not trigger network calls by themselves.

Both URLs point to learn.microsoft.com pages in a documentation section. There is no code that fetches or posts data to those URLs.

Low

SKILL.md:3 SKILL.md:34-43 references/sdk/azure-ai-vision-imageanalysis-py.md:27-28

False Positive: Weak Cryptography Keyword Match

The weak cryptography alerts are keyword collisions in ordinary Azure AI text, such as analysis, linguistic analysis, and caption guidance.

The reviewed lines contain service descriptions and best practices, not hashing, encryption, or cryptographic API usage.

Low

SKILL.md:12-14 references/sdk/azure-ai-translation-ts.md:14-15 SKILL.md:66-67

False Positive: Combined Critical Heuristic

The critical heuristic combines separate documentation signals. Review found no malicious intent, prompt injection, credential theft, or hidden execution path.

The combined signals are legitimate documentation examples and official links. No semantic evidence supports the scanner heuristic as a real threat.

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