flyte-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 untrusted user-provided Flyte source code to generate ZenML project files. • Ingestion points: Flyte task and workflow Python files, LaunchPlan definitions, and container configuration files provided by the user as described in Phase 1 of the migration workflow (SKILL.md). • Capability inventory: The skill generates a complete project directory structure, writes Python, YAML, and TOML files, and executes
zenml init(SKILL.md). • Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the ingested code to prevent potential prompt injection from influencing the agent's output. • Sanitization: No specific sanitization, validation, or escaping of the input source code is implemented before it is processed and interpolated into the generated output files.
Audit Metadata