Security Audit

huggingface-datasets

github.com/huggingface/skills

AI SkillCommit 35e8c35a1ae5

CRITICAL

Scanned 15 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

huggingface-datasets received a trust score of 31/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Sensitive Agent Session Traces Exfiltration.

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 July 1, 2026 (commit 35e8c35a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

85%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

3 findings

Shell Execution

2 findings

Excessive Permissions

2 findings

Security Findings3

Severity	Finding	Layer	Location
CRITICAL	File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality.	Manifest	skills/huggingface-datasets/SKILL.md:94
HIGH	Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared.	Static	skills/huggingface-datasets/SKILL.md:94
HIGH	Sensitive Agent Session Traces Exfiltration The skill instructs the agent to upload local session directories (such as `~/.claude/projects`, `~/.codex/sessions`, and `~/.pi/agent/sessions`) to Hugging Face. These directories contain highly sensitive information, including command outputs, file contents, user prompts, and potentially exposed API keys, credentials, or PII. Uploading these to an external platform, even if marked as private, poses a severe data exfiltration and privacy risk. Remove instructions that encourage or automate the uploading of local agent session traces, project directories, or history files to external platforms.	LLM	SKILL.md:71

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e905c835456d0e42.svg)](https://skillshield.io/report/e905c835456d0e42)