Security Audit

huggingface-best

github.com/huggingface/skills

AI SkillCommit 80f9fa530e46

CAUTION

Scanned 14 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

huggingface-best received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Shell Command Injection via Untrusted API Inputs, Exposure of Hugging Face Token in Process List.

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 October 1, 2026 (commit 80f9fa53). 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

2 findings

Shell Execution

2 findings

Dynamic Code

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Shell Command Injection via Untrusted API Inputs The skill instructs the agent to execute shell commands using variables (<namespace>, <repo>, and model IDs) retrieved from external Hugging Face APIs. If an attacker publishes a malicious dataset or model with shell metacharacters (e.g., containing backticks or semicolons), it could lead to arbitrary command execution when the agent runs the constructed shell command. Avoid executing raw shell commands with dynamically inserted variables. Instead, use a secure programming language (like Python) with the official `huggingface_hub` library, or ensure strict validation/sanitization of the dataset and model IDs (e.g., allowing only alphanumeric characters, hyphens, underscores, and forward slashes) before passing them to a shell.	LLM	SKILL.md:51
MEDIUM	Exposure of Hugging Face Token in Process List The skill instructs the agent to run curl commands with the Hugging Face token evaluated inline. This passes the sensitive API token as a command-line argument, making it visible to any local user or process monitoring tool via the system process list (e.g., ps aux). Pass the token via an environment variable (e.g., `HF_TOKEN`) or use a secure configuration file/library instead of embedding the token directly in shell command arguments.	LLM	SKILL.md:37

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/46be7ecb1bddddd0.svg)](https://skillshield.io/report/46be7ecb1bddddd0)