Build

Name: Claude-plugins/team-build
Author: Fleron

Share on X Share on LinkedIn Share on Bluesky

100Critical

This skill enables arbitrary code execution and system compromise by executing user-defined plans from arbitrary file paths.

ThreatsCI SM CS BC S HITL

Behavior Analysis

Description verified — behavior matches claim

Claims to do

Build: Follow the `Workflow` to implement the `PATH_TO_PLAN` then `Report` the completed work.

Actually does

The skill reads the file specified by `PATH_TO_PLAN`. It then instructs the AI model to interpret and 'implement' the plan's content into the codebase, and to extract a 'Report' section from the plan.

Threat Analysis

AI Agent Traps ↗Scanned 4/15/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction1 finding

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

NameFleron/Claude-plugins/team-build

Registrygithub

Version5662b3e1543f

PURLpkg:github/Fleron/Claude-plugins@5662b3e1543f?skill=team-build

Installs455,628

Source

Repository ↗SKILL.md ↗

SHA-256a76ed80706c5...

SHA-1fd990354a815...

MD5ce4968728218...

TLSH80f0972931c1...

Size506 bytes

Install

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

GitHub

https://github.com/Fleron/Claude-plugins/tree/main/skills/team-build

455,628 installs

Claude CodeDocs

/plugin marketplace add Fleron/Claude-plugins

/plugin install team-build@Fleron/Claude-plugins

Skills.shDocs

npx skills add https://github.com/Fleron/Claude-plugins --skill team-build

Assessments (1)

AI Agent Traps ↗

Arbitrary code execution via user-provided plancriticalcommand execution

The skill is designed to read and execute an arbitrary 'plan' specified by the user via `PATH_TO_PLAN`. This allows an attacker to provide a path to a malicious script or file containing commands, leading to arbitrary code execution, data exfiltration, persistence, or system compromise on the host system.

100% confidenceline 18

- Read and execute the plan at `PATH_TO_PLAN`.

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/team-build.svg)](https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/team-build)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/team-build"><img src="https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/team-build.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/team-build.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