Security Audit

frankxai/claude-skills-library:free-skills/higgsfield-marketplace-cards

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-marketplace-cards received a trust score of 21/100, 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: 2 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Shell Command Injection via Untrusted User Input.

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 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

78%

Behavioral Risk Signals

Network Access

2 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-marketplace-cards/SKILL.md:9
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-marketplace-cards/SKILL.md:9
HIGH	Shell Command Injection via Untrusted User Input The skill instructs the LLM to construct and execute a Bash command (`higgsfield marketplace-cards create`) incorporating raw user input directly into the `--prompt` and other arguments (e.g., `--prompt "<short product and listing intent>"`). If a user provides a prompt containing shell metacharacters (such as double quotes, backticks, or semicolons), it can lead to arbitrary command execution on the host system. Instruct the LLM to strictly sanitize and shell-escape all user-provided values (such as the prompt, category, brand_context, etc.) before executing the command, or use single quotes and escape any single quotes within the user input.	LLM	SKILL.md:50
MEDIUM	Unpinned Remote Script Execution (curl \| sh) The bootstrap instructions direct the LLM to install the `higgsfield` CLI by downloading and piping an unpinned shell script directly from GitHub (`curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh`). If the upstream repository or the network path is compromised, this can result in arbitrary code execution on the user's machine. Pin the installer script to a specific commit hash or release version, or prompt the user to install the CLI manually rather than executing an unverified remote script automatically.	LLM	SKILL.md:8

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/20fb6ced168931c1.svg)](https://skillshield.io/report/20fb6ced168931c1)