marketplace-recsys-feature-engineering
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily composed of documentation and educational content for machine learning engineering. The code examples provided are illustrative and demonstrate best practices for data handling, feature extraction, and model evaluation without executing sensitive operations.
- [INDIRECT_PROMPT_INJECTION]: The skill outlines patterns for processing untrusted user-generated content, such as listing descriptions and sitter wizard responses. This represents a known attack surface for indirect prompt injection. However, the skill explicitly mandates mitigation strategies, including PII scrubbing, regex-based sanitization (e.g., in
quality-scrub-pii-before-features-leave-secure-zone.md), and structured data validation, which are aligned with security best practices. - [EXTERNAL_DOWNLOADS]: The skill references and provides links to authoritative external sources, including engineering blogs and academic papers from well-known technology organizations such as Google, Airbnb, Uber, and Netflix. These references are used for educational purposes and do not involve the download of executable malicious payloads.
Audit Metadata