Skip to main content

Security Audit

herobrine

github.com/aaarnv/claude-skills
AI SkillCommit e47452f4f173
10
CRITICAL
Scanned 14 days ago
14
Critical
Immediate action required
15
High
Priority fixes suggested
6
Medium
Best practices review
2
Low
Acknowledged / Tracked

Trust Assessment

herobrine received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 37 findings: 14 critical, 15 high, 6 medium, and 2 low severity. Key findings include Persistence / self-modification instructions, File read + network send exfiltration, Sensitive environment variable access: $HOME.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.

Last analyzed on June 1, 2026 (commit e47452f4). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis
0%
Static Code Analysis
0%
Dependency Graph
100%
LLM Behavioral Safety
100%

Behavioral Risk Signals

Network Access
12 findings
Filesystem Write
29 findings
Shell Execution
22 findings
Dynamic Code
7 findings
Excessive Permissions
29 findings

Security Findings37

SeverityFindingLayerLocation

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b2a77ac1b5cef61e.svg)](https://skillshield.io/report/b2a77ac1b5cef61e)
SkillShield Badge

Powered by SkillShield