airflow-hitl

Name: agents/airflow-hitl
Author: astronomer

Share on X Share on LinkedIn Share on Bluesky

100Critical

The skill performs unauthorized network exfiltration of environment secrets and executes unconstrained system commands without declaring necessary tool permissions or security boundaries.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/29/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction4 findings

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

HygienePackaging & Manifest1 finding

Skill Info

Nameastronomer/agents/airflow-hitl

Registrygithub

Versiond33a14ddd4cd

PURLpkg:github/astronomer/agents@d33a14ddd4cd?skill=airflow-hitl

Stars393

Installs731

Source

Repository ↗SKILL.md ↗

Install

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

GitHub

731 installs

Skills.shDocs

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

Assessments (3)

AI Agent Traps ↗

Environment secret flows to a network sink (exfiltration)criticaldata exfiltrationAML.T0025AML.T0024LLM02:2025

Environment secret flows to a network sink (exfiltration)

95% confidenceline 11

taint source (line 3): os.environ["AIRFLOW_HOST"] → sink: requests.patch(
    f"{HOST}/<path>/{dag_id}/{run_id}/{task_id}",
    headers=HEADERS,
    json={"chosen_options": ["Approve"], "params_input": {"comments": "ok"}},
)

Outbound network request primitive in skill code — can transmit data externallylowdata exfiltrationAML.T0025AML.T0024LLM02:2025

Outbound network request primitive in skill code — can transmit data externally

95% confidenceline 8

requests.get(f"{HOST}/<path>", headers=HEADERS, params={"state": "pending"})

Missing allowed-tools declarationlowunauthorized tool useAML.T0053LLM06:2025

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 useAML.T0053LLM06:2025

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

60% confidence

Missing licenseinfopolicy violation

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

100% confidence

Version History (2)

d33a14ddd4cdcurrent100Critical6/29/2026 da0048c49f8840Medium6/20/2026

Badge

Markdown

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

HTML

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

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/airflow-hitl.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