Versioned security assessment

Report ID: SA-DD48A85E

6/30/2026, 11:21:48 AM

agent-framework-azure-ai-py security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
agent-framework-azure-ai-py
Version
v2
Maintainer
sickn33
Source
github.com/sickn33/antigravity-awesome-skills/tree/main/skills/agent-framework-azure-ai-py
Coverage
1 Files scanned · 334 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.

Most static findings are false positives caused by Markdown fences, Python imports, and Python async context managers in documentation examples. The skill is still medium risk because it instructs users to configure hosted code execution, web search, and MCP network tools for Azure AI agents.

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 · 334 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 9 evidence locations

Network access

May connect to external services.

Observed in 2 evidence locations

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 40 evidence locations

Capability review items (2)
Medium
SKILL.md:130-134SKILL.md:273-286
Hosted Code, Web Search, and MCP Tool Enablement
The skill demonstrates hosted code execution, Bing web search, and MCP network tooling inside Azure AI agents. This is legitimate agent development guidance, but deployments should restrict tool permissions, review outbound endpoints, and avoid sending sensitive data to hosted tools.
The referenced examples explicitly configure hosted code, web search, and MCP tools. The intent appears educational rather than malicious, so the concern is operational risk rather than confirmed abuse.
Low
SKILL.md:36SKILL.md:275
Hardcoded Example Service URLs
The skill includes an Azure project endpoint placeholder and a Microsoft Learn MCP endpoint in examples. These are not evidence of credential exfiltration, but users should verify endpoints before production use.
The URLs are visible in documentation examples and point to Azure or Microsoft services. No evidence found that they collect secrets or route traffic to an unrelated destination.

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.

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