data-engineering-data-driven-feature
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input through the $ARGUMENTS placeholder across multiple development phases.
- Ingestion points: The $ARGUMENTS variable in SKILL.md is directly embedded in prompts for several specialized subagents.
- Boundary markers: There are no delimiters or specific instructions to isolate user input from the rest of the prompt, which could allow instructions within the input to be executed by the subagents.
- Capability inventory: The involved subagents have the ability to generate code (backend/frontend), configure infrastructure (deployment-engineer), and design data pipelines.
- Sanitization: No input validation or sanitization is performed on the user-provided arguments.
Audit Metadata