data-engineering-data-driven-feature
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable to pass user input directly into the prompts of multiple specialized subagents (e.g.,data-scientist,business-analyst,backend-architect) without using delimiters or boundary markers. This represents a surface for indirect prompt injection where malicious input could attempt to override the subagents' specialized instructions. - Ingestion points: The
$ARGUMENTSvariable is interpolated into prompts across Phase 1 through Phase 6 inSKILL.md. - Boundary markers: None present; user input is concatenated directly into the instructional string.
- Capability inventory: The targeted subagents are designed to perform complex tasks including data analysis, architecture design, and code implementation.
- Sanitization: No validation or escaping of the
$ARGUMENTScontent is performed before interpolation.
Audit Metadata