Security Audit

frankxai/claude-skills-library:free-skills/higgsfield-product-photoshoot

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-product-photoshoot received a trust score of 14/100, 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, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Command Injection via User-Supplied Prompt in Shell Command.

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

70%

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-product-photoshoot/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-product-photoshoot/SKILL.md:12
HIGH	Command Injection via User-Supplied Prompt in Shell Command The skill instructs the LLM to construct and execute a shell command (`higgsfield product-photoshoot create`) incorporating raw user-supplied input (`<short user-intent description from interview answers>`) inside double quotes. If a user provides input containing shell metacharacters (such as double quotes, semicolons, or backticks), it can break out of the command context and execute arbitrary shell commands in the host environment. Ensure that any user-supplied input is strictly sanitized or escaped before being passed to a shell command, or use a safe execution mechanism that passes arguments as an array rather than evaluating them in a shell.	LLM	SKILL.md:119
HIGH	Arbitrary Code Execution via Unverified Remote Script Installation The bootstrap instructions direct the LLM to automatically download and execute a shell script from a remote repository (`curl -fsSL https://raw.githubusercontent.com/... \| sh`) if the CLI is not found in the PATH. This pattern introduces a severe supply chain risk, as the remote script could be compromised or modified to execute malicious code on the user's machine without prior verification. Avoid automatically downloading and piping remote scripts to a shell. Instead, instruct the user to install the required CLI tool themselves, or perform integrity checks (such as verifying a cryptographic hash) before executing downloaded scripts.	LLM	SKILL.md:11

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/890a67287d521aef.svg)](https://skillshield.io/report/890a67287d521aef)