100Critical
The skill is malicious, enabling SQL injection and unauthorized Airflow CLI command execution while forcing unverified dependencies to bypass security controls and exfiltrate sensitive pipeline metadata.
Skill Info
Nameastronomer/agents/checking-freshness
Registrygithub
Versionda0048c49f88
PURLpkg:github/astronomer/agents@da0048c49f88?skill=checking-freshness
Stars391
Installs759
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
759 installs
Skills.shDocs
npx skills add https://github.com/astronomer/agentsAssessments (3)
AI Agent Traps ↗SQL injection — database system-object or file-access abuse (information_schema/xp_cmdshell/INTO OUTFILE/LOAD_FILE) detectedcriticalsql injectionAML.T0050AML.T0053LLM05:2025
SQL injection — database system-object or file-access abuse (information_schema/xp_cmdshell/INTO OUTFILE/LOAD_FILE) detected
100% confidenceline 22
INFORMATION_SCHEMA.COLUMNS
Implicit privilege escalation via tool chainingmediumoversight evasionAML.T0054LLM01:2025LLM07:2025
By directing the agent to use 'af dags list' and 'af dags get', the skill assumes the agent has pre-configured CLI access to Airflow/Astro environments, potentially exposing sensitive pipeline metadata without explicit user authorization for those specific tools.
70% confidence
Use `af dags list` and `af dags get <dag_id>`
Cross-skill dependency injectionmediumsub agent spawningAML.T0053AML.T0051.001LLM06:2025
The skill explicitly instructs the agent to invoke a separate, external skill ('debugging-dags') if data is stale, creating a hard-coded dependency on an unverified third-party component.
80% confidenceline 102
Action: Investigate with **debugging-dags** skill
Description Mismatchhighdescription mismatchAML.T0011.000LLM06:2025LLM09:2025
The skill includes instructions to execute arbitrary Airflow CLI commands and cross-references another skill, which exceeds the stated purpose of a simple data freshness check and introduces potential command injection or unauthorized system interaction risks.
85% confidence
The 'If Data is Stale' section explicitly directs the use of 'af dags list', 'af dags get', and 'af dags stats' commands.
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/astronomer/agents/checking-freshness)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/astronomer/agents/checking-freshness"><img src="https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/checking-freshness.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/astronomer/agents/checking-freshness.svgSecure 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