Security Audit

frankxai/claude-skills-library:free-skills/higgsfield-generate

github.com/frankxai/claude-skills-library

AI SkillCommit 93c4aad53fe8

CRITICAL

Scanned 1 day ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

frankxai/claude-skills-library:free-skills/higgsfield-generate 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, 0 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Arbitrary Command Injection via Unsanitized User Inputs in Bash Tool Calls.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, indicating areas for improvement.

Last analyzed on October 20, 2026 (commit 93c4aad5). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

70%

Dependency Graph

100%

LLM Behavioral Safety

63%

Behavioral Risk Signals

Network Access

3 findings

Filesystem Write

1 finding

Shell Execution

4 findings

Dynamic Code

1 finding

Security Findings4

Severity	Finding	Layer	Location
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	free-skills/higgsfield-generate/SKILL.md:12
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	free-skills/higgsfield-generate/SKILL.md:12
CRITICAL	Arbitrary Command Injection via Unsanitized User Inputs in Bash Tool Calls The skill instructions direct the LLM to construct and execute shell commands (using the Bash tool) containing user-provided inputs (such as prompts, URLs, titles, and image paths) without specifying any escaping or sanitization. If a user provides an input containing shell metacharacters (e.g., ';', '&&', '\|', backticks, or '$()'), it will result in arbitrary command execution on the host system. Instruct the LLM to carefully escape all user-controlled variables before passing them to the shell, or use safe APIs/wrappers that do not invoke a shell interpreter directly. For example, use single quotes and escape any single quotes within the user input, or write the arguments to a temporary file and read them, or use a structured tool instead of raw Bash execution.	LLM	SKILL.md:100
MEDIUM	Unverified Remote Script Execution (Curl to Sh) The bootstrap instructions tell the LLM to download and execute a shell script directly from a remote GitHub repository (https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh) without verifying its integrity (e.g., via a SHA-256 checksum) or asking for explicit user confirmation before running arbitrary remote code. Avoid piping remote scripts directly to sh. Instead, prompt the user to install the CLI themselves, or download the script, display it/verify its checksum, and then execute it after explicit user confirmation.	LLM	SKILL.md:14

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/3566a31beace09db.svg)](https://skillshield.io/report/3566a31beace09db)