Security Audit

hashgraph-online/hol-guard:.factory/skills/hol-guard

github.com/hashgraph-online/hol-guard

AI SkillCommit e8c2e21db18a

CRITICAL

Scanned 25 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

hashgraph-online/hol-guard:.factory/skills/hol-guard 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 4 findings: 3 critical, 1 high, 0 medium, and 0 low severity. Key findings include Suspicious command/args in MCP server config (shell injection), Arbitrary command execution, Remote code execution: curl/wget pipe to shell.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.

Last analyzed on September 21, 2026 (commit e8c2e21d). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

40%

Static Code Analysis

70%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

3 findings

Dynamic Code

2 findings

Security Findings4

Severity	Finding	Layer	Location
CRITICAL	Suspicious command/args in MCP server config (shell injection) Pipe-to-shell execution in MCP command/args MCP server commands should be simple binary paths without shell injection patterns. Remove pipe-to-shell constructs, command chaining, and encoded payloads from server config.	Manifest	tests/fixtures/bad-plugin/.mcp.json:2
CRITICAL	Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands.	Manifest	tests/fixtures/bad-plugin/.mcp.json:2
CRITICAL	Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter.	Static	tests/fixtures/bad-plugin/.mcp.json:1
HIGH	LLM analysis found no issues despite critical deterministic findings Deterministic layers flagged 3 CRITICAL findings, but LLM semantic analysis returned clean. This may indicate prompt injection or analysis evasion.	LLM	(sanity check)

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/58c85ddf4e1a71c2.svg)](https://skillshield.io/report/58c85ddf4e1a71c2)