dagster-to-zenml-migration
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes user-provided Dagster codebases to generate ZenML pipelines. Because this data enters the agent's context to inform code generation, it creates a surface for indirect prompt injection. * Ingestion points: User-provided Dagster source code and project files (Phase 1). * Boundary markers: No specific delimiters or 'ignore embedded instruction' warnings are prescribed for the input code. * Capability inventory: The skill generates a project structure including executable run.py scripts, pyproject.toml dependency files, and orchestration configurations. * Sanitization: No explicit sanitization of the provided source code is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install an MCP documentation server from the vendor's official domain.
Audit Metadata