db-seed-generator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process
schema.prismaandconfig/defaults.md, which serves as an ingestion point for potentially untrusted data that could influence the generated output script. - Ingestion points: The skill reads
schema.prismaandconfig/defaults.mdfrom the local environment. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions hidden within comments or data in these files.
- Capability inventory: The skill produces a
prisma/seed.tsfile meant for execution by the user or an automated pipeline. - Sanitization: The process lacks mechanisms to sanitize or validate the schema data against malicious injection before code generation.
- [DYNAMIC_EXECUTION]: The skill creates an executable TypeScript script (
prisma/seed.ts) at runtime based on external definitions.
Audit Metadata