metaflow-to-zenml-migration
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Metaflow code and configuration files, creating an attack surface for indirect prompt injection.\n
- Ingestion points: Phase 1 instructions in
SKILL.mddirect the agent to receive and analyze external flow files and supporting modules.\n - Boundary markers: The instructions do not specify the use of delimiters or ignore-behavior markers to isolate user-provided code.\n
- Capability inventory: The skill instructions include file creation/project structure generation (Phase 3) and text generation for external platforms (Phase 5).\n
- Sanitization: The skill lacks instructions for the agent to sanitize or validate the external content before it is processed or used in generated reports.
Audit Metadata