data-pipeline-architect
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines architectures for ingesting and processing data from various external sources (APIs, databases, and file systems) which could contain untrusted input.
- Ingestion points: External source systems such as REST APIs, SQL databases, and cloud storage (S3) are identified as primary entry points in
SKILL.mdandreferences/pipeline-templates.md. - Boundary markers: The conceptual templates do not explicitly define LLM-specific boundary markers for data processing.
- Capability inventory: The skill provides instructions for the agent to design and potentially implement data movement and transformation logic.
- Sanitization: The skill provides extensive documentation on data quality frameworks and validation rules in
references/data-quality-checks.md, which includes validity, consistency, and format checks that serve to sanitize data at the application layer.
Audit Metadata