recsys-pipeline-architect
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external repository (github.com/mturac/recsys-pipeline-architect) as its upstream source and suggests an installation command (npx skills add mturac/recsys-pipeline-architect) which fetches code from a public GitHub account.
- [DYNAMIC_EXECUTION]: The skill is designed to generate functional code scaffolds in various languages (TypeScript, Go, Python) to implement recommendation pipelines based on user specifications.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requirements to generate architecture and code, creating an attack surface where malicious input could influence the generated output. \n
- Ingestion points: Step 1 of the workflow (items being ranked, input context, language/runtime) in SKILL.md. \n
- Boundary markers: None present in the instructions to delimit user input or prevent execution of embedded instructions. \n
- Capability inventory: Writing executable code scaffolds (TypeScript, Go, Python) as described in Step 8 and the Upstream contents section. \n
- Sanitization: No explicit sanitization or validation of user-provided strings is mentioned before they are interpolated into the generated code.
Audit Metadata