Security Audit

azure-ai-transcription-py

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

azure-ai-transcription-py received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential arbitrary file read via `send_audio_file`, Potential Server-Side Request Forgery (SSRF) via `content_urls`.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential arbitrary file read via `send_audio_file` The skill demonstrates using `stream.send_audio_file("audio.wav")`. If the filename or path passed to `send_audio_file` can be influenced by untrusted user input, an attacker could potentially make the skill read arbitrary files from the host system. This could lead to data exfiltration if the content of these files is then processed by the Azure service. Ensure that any file paths provided to `stream.send_audio_file` are strictly validated and sanitized, or that the skill only operates on files within a secure, isolated directory. Avoid directly using user-provided paths without validation.	LLM	SKILL.md:49
MEDIUM	Potential Server-Side Request Forgery (SSRF) via `content_urls` The batch transcription example uses `content_urls=["https://<storage>/audio.wav"]`. If the `<storage>` part of the URL can be influenced by untrusted user input, an attacker could potentially make the skill fetch content from arbitrary internal or external URLs. This could lead to information disclosure (e.g., internal network scanning, accessing cloud metadata endpoints) or other SSRF-related attacks. Strictly validate and sanitize all URLs provided to `content_urls`. Implement a whitelist of allowed domains or ensure that URLs point only to trusted storage locations. Prevent access to internal network resources or sensitive external endpoints.	LLM	SKILL.md:38

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/51ed86082cf79e25.svg)](https://skillshield.io/report/51ed86082cf79e25)