data-engineering-data-driven-feature
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-supplied data from the
$ARGUMENTSvariable directly into instructions for multiple specialized sub-agents throughout the entire development lifecycle. - Ingestion points: User input provided to the
$ARGUMENTSvariable inSKILL.mdis passed into 16 separate task prompts across six phases. - Boundary markers: Absent. User input is not wrapped in delimiters (such as triple-backticks or specific XML tags) nor are the sub-agents instructed to ignore potential commands embedded within the feature description.
- Capability inventory: The workflow coordinates sub-agents with roles in backend and frontend development, data engineering, and infrastructure deployment, which typically possess capabilities for code execution, database access, and environment configuration.
- Sanitization: The skill does not implement any validation, filtering, or escaping of the
$ARGUMENTScontent before it is processed by the sub-agents.
Audit Metadata