airflow-plugins

100Critical

The skill exfiltrates environment secrets to external network sinks while bypassing security constraints by executing unauthorized network requests and file operations without declaring required tool permissions.

Threat Analysis

AI Agent Traps ↗Scanned 6/29/2026
Content InjectionPerceptionclean
Semantic ManipulationReasoningclean
Cognitive StateMemory & Learningclean
SystemicMulti-Agent Dynamicsclean
Human-in-the-LoopHuman Overseerclean
HygienePackaging & Manifest1 finding

Skill Info

Nameastronomer/agents/airflow-plugins
Registrygithub
Versiond33a14ddd4cd
PURLpkg:github/astronomer/agents@d33a14ddd4cd?skill=airflow-plugins
Stars393
Installs380

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
GitHub
380 installs
Skills.sh
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 20
taint source (line 8): os.environ.get("MYPLUGIN_HOST",     "http://localhost:8080") → sink: requests.post(
        f"{AIRFLOW_HOST}/auth/token",
        json={"username": AIRFLOW_USER, "password": AIRFLOW_PASS},
        timeout=10,
    )
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 7
requests.get(f"https://files.example.com/{filename}", stream=True)
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 (seen 2 times in this file at lines 1, 2)

95% confidenceline 1
fetch('api/dags')
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 20
requests.post(
        f"{AIRFLOW_HOST}/auth/token",
        json={"username": AIRFLOW_USER, "password": AIRFLOW_PASS},
        timeout=10,
    )
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

Badge

Skill Check badge
Markdown
[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/airflow-plugins.svg)](https://mondoo.com/ai-agent-security/skills/github/astronomer/agents/airflow-plugins)
HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/astronomer/agents/airflow-plugins"><img src="https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/airflow-plugins.svg" alt="Mondoo Skill Check" /></a>
Image URL
https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/airflow-plugins.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, discover and control Shadow AI usage.

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

By submitting, you agree to our privacy policy.