data-engineering-data-driven-feature
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by interpolating user-provided arguments ($ARGUMENTS) into prompts for subagents that perform high-privilege tasks such as code generation and deployment configuration.
- Ingestion points: The $ARGUMENTS variable is used to provide context to subagents across multiple phases in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters used to separate user-provided data from agent instructions, increasing the risk that malicious content in the arguments could be interpreted as commands by the subagents.
- Capability inventory: Subagents are tasked with backend and frontend code implementation (Steps 7, 8), machine learning pipeline integration (Step 9), and infrastructure configuration (Step 11).
- Sanitization: The skill does not define any input validation or sanitization mechanisms for the external data passed via arguments.
Audit Metadata