higgsfield-marketplace-cards

Name: skills/higgsfield-marketplace-cards
Author: higgsfield-ai

Share on X Share on LinkedIn Share on Bluesky

100Critical

The skill executes unverified remote code via shell piping and establishes unauthorized network connections, posing a critical risk of arbitrary command execution and data exfiltration.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/29/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction3 findings

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

HygienePackaging & Manifest1 finding

Skill Info

Namehiggsfield-ai/skills/higgsfield-marketplace-cards

Registrygithub

Version7c04e10f8a60

PURLpkg:github/higgsfield-ai/skills@7c04e10f8a60?skill=higgsfield-marketplace-cards

Stars492

Installs56,900

Source

Repository ↗SKILL.md ↗

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.

GitHub

56,900 installs

Skills.shDocs

npx skills add https://github.com/higgsfield-ai/skills

Assessments (3)

AI Agent Traps ↗

Remote code download and execution detectedcriticalremote execAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025

Remote code download and execution detected

95% confidenceline 26

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

Unverified remote script executionhighsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025

The skill instructs the agent to install the CLI by piping a remote script directly into a shell, which is an unpinned and unverified execution pattern. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]

90% confidenceline 26

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

Network access detectedmediumunauthorized tool useAML.T0053LLM06:2025

Code contains network access patterns (HTTP requests, socket connections).

80% confidence

Missing licenseinfopolicy violation

Skill does not specify a license field. Specifying a license helps users understand usage terms.

100% confidence

Version History (2)

7c04e10f8a60current100Critical6/29/2026 5035913ca3fb100Critical6/20/2026

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/higgsfield-ai/skills/higgsfield-marketplace-cards.svg)](https://mondoo.com/ai-agent-security/skills/github/higgsfield-ai/skills/higgsfield-marketplace-cards)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/higgsfield-ai/skills/higgsfield-marketplace-cards"><img src="https://mondoo.com/ai-agent-security/api/badge/github/higgsfield-ai/skills/higgsfield-marketplace-cards.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/higgsfield-ai/skills/higgsfield-marketplace-cards.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow