recsys-pipeline-architect
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository belonging to a community member for additional resources and includes instructions for manual installation via an external source (
github.com/mturac/recsys-pipeline-architect).- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided context into generated code scaffolds, creating a surface for potential indirect prompt injection attacks. - Ingestion points: The workflow in Step 1 processes user-defined "items being ranked" and "input context" from the conversation history.
- Capability inventory: The skill is designed to generate functional code scaffolds in TypeScript, Go, and Python, which are then executed or managed by the user.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat user-supplied context as untrusted data or to ignore embedded instructions.
- Sanitization: The instructions do not specify any validation, escaping, or sanitization of the user-provided context before it is interpolated into the generated code.
Audit Metadata