recsys-pipeline-architect
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-defined item types and context variables which are interpolated into generated code scaffolds. This represents an attack surface for indirect prompt injection, although the behavior is inherent to the skill's purpose as a code generator.
- Ingestion points: User-provided answers to questions about ranking items and context in SKILL.md.
- Boundary markers: None identified.
- Capability inventory: Code generation for multiple languages.
- Sanitization: None described.
- [DYNAMIC_EXECUTION]: The skill generates runnable code scaffolds in TypeScript, Go, and Python based on user specifications. The generated code follows predefined structural patterns for recommendation pipelines.
- [EXTERNAL_DOWNLOADS]: The skill references an external community repository (github.com/mturac/recsys-pipeline-architect) and suggests installation via a package manager tool for additional documentation and example scaffolds.
Audit Metadata