cosmos-dbt-fusion

Name: agents/cosmos-dbt-fusion
Author: astronomer

Share on X Share on LinkedIn Share on Bluesky

100Critical

The skill executes unverified remote shell scripts and performs unauthorized network and file operations, creating a critical security risk through arbitrary code execution and lack of tool constraints.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/20/2026

Content InjectionPerception1 finding

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction1 finding

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Nameastronomer/agents/cosmos-dbt-fusion

Registrygithub

Versionda0048c49f88

PURLpkg:github/astronomer/agents@da0048c49f88?skill=cosmos-dbt-fusion

Stars391

Installs669

Source

Repository ↗SKILL.md ↗

Install

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

GitHub

669 installs

Skills.shDocs

npx skills add https://github.com/astronomer/agents

Assessments (4)

AI Agent Traps ↗

Remote code download and execution detectedcriticalcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025

Remote code download and execution detected

100% confidenceline 54

curl -fsSL https://public.cdn.getdbt.com/fs/install/install.sh | sh

Indirect prompt injection via external install scripthighindirect prompt injection

The skill instructs the user to execute a shell script from a remote URL (getdbt.com) via pipe-to-sh, which is an unverified and mutable external source that can execute arbitrary code with the privileges of the Airflow user.

90% confidenceline 54

curl -fsSL https://public.cdn.getdbt.com/fs/install/install.sh | sh -s -- --update

Missing allowed-tools declarationlowunauthorized tool use

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence

Undeclared network usagelowunauthorized tool use

Skill contains network access patterns (HTTP requests, socket connections) without declaring network capability in allowed-tools.

60% confidence

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "reference/cosmos-config.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime

90% confidence

[reference/cosmos-config.md](reference/cosmos-config.md)

Missing licenseinfopolicy violation

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

100% confidence

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/cosmos-dbt-fusion.svg)](https://mondoo.com/ai-agent-security/skills/github/astronomer/agents/cosmos-dbt-fusion)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/astronomer/agents/cosmos-dbt-fusion"><img src="https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/cosmos-dbt-fusion.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/cosmos-dbt-fusion.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