migrating-airflow-2-to-3

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run ruff commands (e.g., ruff check --preview --select AIR --fix --unsafe-fixes .) to automate the migration process. These are standard development tools used for their intended purpose in a migration workflow.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation from Astronomer and the Apache Airflow project. It also recommends installing the official apache-airflow-client package via pip or requirements.txt. These resources originate from well-known and trusted entities within the Airflow ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions by analyzing and modifying user-provided codebase (Airflow DAGs), which introduces a potential surface for indirect prompt injection if the code being processed contains malicious instructions.
  • Ingestion points: User-provided Airflow DAG files and project configuration files (SKILL.md).
  • Boundary markers: The skill does not explicitly instruct the agent to use boundary markers or delimiters when processing code files.
  • Capability inventory: The skill involves file system modifications (implied for migration) and shell command execution (ruff).
  • Sanitization: No explicit sanitization or validation steps are provided for the content of the DAG files before they are processed by the migration logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:37 PM