backend-prisma-repository
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes user-controlled source code to generate and modify files.
- Ingestion points: Repository interface files located in the 'modules/' directory (e.g., 'modules//src/**').
- Boundary markers: The skill does not define specific delimiters or instructional boundaries to isolate the external source code from the agent's internal logic.
- Capability inventory: The agent has the capability to create new TypeScript files ('.prisma.ts') and modify existing NestJS module files to register and export providers.
- Sanitization: No explicit sanitization or filtering is performed on the content of the interfaces being read, which could allow malicious instructions in comments to influence the generated output.
Audit Metadata