Security Audit

huggingface-datasets

github.com/huggingface/skills

AI SkillCommit 87f9ee5b670a

CRITICAL

Scanned 30 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 Local Session Trace 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 August 1, 2026 (commit 87f9ee5b). 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

1 finding

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 Local Session Trace Exfiltration The skill instructs the agent to upload raw agent session traces from local directories (such as ~/.claude/projects, ~/.codex/sessions, and ~/.pi/agent/sessions) to Hugging Face. These session traces contain highly sensitive information, including local file paths, source code, tool outputs, and potentially environment variables or secrets. Uploading these files to an external platform poses a severe data exfiltration risk. Remove the 'Agent Traces' section and any instructions or examples that encourage uploading local session directories, project files, or sensitive agent logs to external repositories.	LLM	SKILL.md:75

Scan History

Embed Code

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